Source-free unsupervised domain adaptation: A survey
Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different domains. Existing UDA approaches highly depend on the accessibility of source domain data, which is usually limited in pract...
Gespeichert in:
| Veröffentlicht in: | Neural networks Jg. 174; S. 106230 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
Elsevier Ltd
01.06.2024
|
| Schlagworte: | |
| ISSN: | 0893-6080, 1879-2782, 1879-2782 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different domains. Existing UDA approaches highly depend on the accessibility of source domain data, which is usually limited in practical scenarios due to privacy protection, data storage and transmission cost, and computation burden. To tackle this issue, many source-free unsupervised domain adaptation (SFUDA) methods have been proposed recently, which perform knowledge transfer from a pre-trained source model to the unlabeled target domain with source data inaccessible. A comprehensive review of these works on SFUDA is of great significance. In this paper, we provide a timely and systematic literature review of existing SFUDA approaches from a technical perspective. Specifically, we categorize current SFUDA studies into two groups, i.e., white-box SFUDA and black-box SFUDA, and further divide them into finer subcategories based on different learning strategies they use. We also investigate the challenges of methods in each subcategory, discuss the advantages/disadvantages of white-box and black-box SFUDA methods, conclude the commonly used benchmark datasets, and summarize the popular techniques for improved generalizability of models learned without using source data. We finally discuss several promising future directions in this field.
•Providing a review of existing source-free unsupervised domain adaptation approaches.•Dividing current methods into finer categories and discussing their (dis)advantages.•Summarizing benchmark datasets and techniques that improve model generalizability.•Discussing promising research directions to guide trajectory of future investigation.•Offering extensive references, serving as a valuable resource in this research field. |
|---|---|
| AbstractList | Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different domains. Existing UDA approaches highly depend on the accessibility of source domain data, which is usually limited in practical scenarios due to privacy protection, data storage and transmission cost, and computation burden. To tackle this issue, many source-free unsupervised domain adaptation (SFUDA) methods have been proposed recently, which perform knowledge transfer from a pre-trained source model to the unlabeled target domain with source data inaccessible. A comprehensive review of these works on SFUDA is of great significance. In this paper, we provide a timely and systematic literature review of existing SFUDA approaches from a technical perspective. Specifically, we categorize current SFUDA studies into two groups, i.e., white-box SFUDA and black-box SFUDA, and further divide them into finer subcategories based on different learning strategies they use. We also investigate the challenges of methods in each subcategory, discuss the advantages/disadvantages of white-box and black-box SFUDA methods, conclude the commonly used benchmark datasets, and summarize the popular techniques for improved generalizability of models learned without using source data. We finally discuss several promising future directions in this field. Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different domains. Existing UDA approaches highly depend on the accessibility of source domain data, which is usually limited in practical scenarios due to privacy protection, data storage and transmission cost, and computation burden. To tackle this issue, many source-free unsupervised domain adaptation (SFUDA) methods have been proposed recently, which perform knowledge transfer from a pre-trained source model to the unlabeled target domain with source data inaccessible. A comprehensive review of these works on SFUDA is of great significance. In this paper, we provide a timely and systematic literature review of existing SFUDA approaches from a technical perspective. Specifically, we categorize current SFUDA studies into two groups, i.e., white-box SFUDA and black-box SFUDA, and further divide them into finer subcategories based on different learning strategies they use. We also investigate the challenges of methods in each subcategory, discuss the advantages/disadvantages of white-box and black-box SFUDA methods, conclude the commonly used benchmark datasets, and summarize the popular techniques for improved generalizability of models learned without using source data. We finally discuss several promising future directions in this field.Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different domains. Existing UDA approaches highly depend on the accessibility of source domain data, which is usually limited in practical scenarios due to privacy protection, data storage and transmission cost, and computation burden. To tackle this issue, many source-free unsupervised domain adaptation (SFUDA) methods have been proposed recently, which perform knowledge transfer from a pre-trained source model to the unlabeled target domain with source data inaccessible. A comprehensive review of these works on SFUDA is of great significance. In this paper, we provide a timely and systematic literature review of existing SFUDA approaches from a technical perspective. Specifically, we categorize current SFUDA studies into two groups, i.e., white-box SFUDA and black-box SFUDA, and further divide them into finer subcategories based on different learning strategies they use. We also investigate the challenges of methods in each subcategory, discuss the advantages/disadvantages of white-box and black-box SFUDA methods, conclude the commonly used benchmark datasets, and summarize the popular techniques for improved generalizability of models learned without using source data. We finally discuss several promising future directions in this field. Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different domains. Existing UDA approaches highly depend on the accessibility of source domain data, which is usually limited in practical scenarios due to privacy protection, data storage and transmission cost, and computation burden. To tackle this issue, many source-free unsupervised domain adaptation (SFUDA) methods have been proposed recently, which perform knowledge transfer from a pre-trained source model to the unlabeled target domain with source data inaccessible. A comprehensive review of these works on SFUDA is of great significance. In this paper, we provide a timely and systematic literature review of existing SFUDA approaches from a technical perspective. Specifically, we categorize current SFUDA studies into two groups, i.e., white-box SFUDA and black-box SFUDA, and further divide them into finer subcategories based on different learning strategies they use. We also investigate the challenges of methods in each subcategory, discuss the advantages/disadvantages of white-box and black-box SFUDA methods, conclude the commonly used benchmark datasets, and summarize the popular techniques for improved generalizability of models learned without using source data. We finally discuss several promising future directions in this field. •Providing a review of existing source-free unsupervised domain adaptation approaches.•Dividing current methods into finer categories and discussing their (dis)advantages.•Summarizing benchmark datasets and techniques that improve model generalizability.•Discussing promising research directions to guide trajectory of future investigation.•Offering extensive references, serving as a valuable resource in this research field. |
| ArticleNumber | 106230 |
| Author | Liu, Mingxia Fang, Yuqi Yap, Pew-Thian Lin, Weili Zhu, Hongtu |
| AuthorAffiliation | a Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States b Department of Biostatistics and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States |
| AuthorAffiliation_xml | – name: a Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States – name: b Department of Biostatistics and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States |
| Author_xml | – sequence: 1 givenname: Yuqi orcidid: 0000-0002-8769-496X surname: Fang fullname: Fang, Yuqi organization: Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States – sequence: 2 givenname: Pew-Thian surname: Yap fullname: Yap, Pew-Thian organization: Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States – sequence: 3 givenname: Weili surname: Lin fullname: Lin, Weili organization: Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States – sequence: 4 givenname: Hongtu surname: Zhu fullname: Zhu, Hongtu organization: Department of Biostatistics and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States – sequence: 5 givenname: Mingxia surname: Liu fullname: Liu, Mingxia email: mingxia_liu@med.unc.edu organization: Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, United States |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38490115$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFUctKxDAUDTKi4-MPRLp00zGvpskslGHwBYILdR0y6a1m6CRj0g7491aqoi50deHe87ics4dGPnhA6IjgCcFEnC4nHjoP7YRiyvuVoAxvoTGRpcppKekIjbFULBdY4l20l9ISYywkZztol0muMCHFGPH70EULeR0Bss6nbg1x4xJUWRVWxvnMVGbdmtYFP81mWeriBl4P0HZtmgSHH3MfPV5ePMyv89u7q5v57Da3XPA2t6xWkppFycAsTMF5WTMlDTEl54oaYYUUQshFURLglgIFrFhtalZjTEFUbB-dD7rrbrGCyoJvo2n0OrqVia86GKd_Xrx71k9ho0mfUKEE7xVOPhRieOkgtXrlkoWmMR5ClzRVhaRKcUp76PF3sy-Xz6x6AB8ANoaUItRfEIL1eyV6qYdK9Hsleqikp01_0awbAu1fds1_5LOBDH3MGwdRJ-vAW6hcBNvqKri_Bd4A43KpvA |
| CitedBy_id | crossref_primary_10_3390_app14114466 crossref_primary_10_1007_s11517_025_03287_0 crossref_primary_10_1631_FITEE_2400467 crossref_primary_10_1038_s42256_024_00961_0 crossref_primary_10_1109_ACCESS_2024_3429415 crossref_primary_10_1109_ACCESS_2025_3592034 crossref_primary_10_1007_s11227_024_06886_0 crossref_primary_10_3390_rs17071302 crossref_primary_10_3390_rs17101693 crossref_primary_10_3390_s25133856 crossref_primary_10_1007_s42452_025_06909_2 crossref_primary_10_1016_j_engappai_2025_111350 crossref_primary_10_1016_j_sigpro_2025_110118 crossref_primary_10_12677_mos_2025_144320 crossref_primary_10_1007_s00138_024_01615_2 crossref_primary_10_1016_j_neucom_2025_129472 crossref_primary_10_1016_j_ins_2025_122608 crossref_primary_10_1109_TMM_2024_3350917 crossref_primary_10_1016_j_neunet_2024_107031 crossref_primary_10_3390_electronics14010051 crossref_primary_10_1109_ACCESS_2024_3454082 crossref_primary_10_1371_journal_pone_0309118 crossref_primary_10_1088_1361_6501_adc6a6 crossref_primary_10_1007_s10994_025_06739_8 crossref_primary_10_1109_JIOT_2025_3554228 crossref_primary_10_1029_2025JH000754 crossref_primary_10_1109_JSTARS_2025_3561737 crossref_primary_10_1109_TIM_2025_3541814 crossref_primary_10_1016_j_engappai_2025_110913 crossref_primary_10_1016_j_eswa_2024_126031 crossref_primary_10_1016_j_neunet_2025_107161 crossref_primary_10_1109_TMRB_2025_3561865 crossref_primary_10_3390_s24248053 crossref_primary_10_1016_j_knosys_2024_112615 crossref_primary_10_1016_j_bspc_2025_108053 crossref_primary_10_1007_s10489_025_06777_8 crossref_primary_10_1016_j_cemconcomp_2025_105943 crossref_primary_10_3390_rs16183469 crossref_primary_10_1007_s10922_025_09927_y crossref_primary_10_1016_j_patcog_2025_112290 crossref_primary_10_1016_j_knosys_2025_112982 crossref_primary_10_1109_TBME_2023_3303289 crossref_primary_10_1016_j_neunet_2024_106958 crossref_primary_10_1109_TCSVT_2025_3525715 crossref_primary_10_1016_j_media_2024_103404 crossref_primary_10_1007_s11263_024_02181_w crossref_primary_10_1109_JIOT_2024_3464854 crossref_primary_10_1109_TCSVT_2025_3538539 crossref_primary_10_3934_acse_2025018 crossref_primary_10_1016_j_ress_2025_111263 crossref_primary_10_1109_TITS_2025_3550862 crossref_primary_10_1016_j_compag_2025_110473 crossref_primary_10_1109_JIOT_2024_3471410 |
| Cites_doi | 10.1002/int.22434 10.1145/3523273 10.1109/ICCV.2019.00683 10.1109/CVPR52729.2023.00343 10.1109/CVPR52688.2022.00701 10.1109/ACCESS.2020.3014264 10.1109/TPAMI.2021.3052758 10.1109/MSP.2020.2975749 10.1016/j.media.2022.102617 10.1109/MCI.2018.2840738 10.1109/TAI.2021.3110179 10.1016/j.neucom.2018.05.083 10.1109/ICCV.2019.00149 10.1109/CVPR42600.2020.00975 10.1109/TMM.2022.3146744 10.1109/ICCV48922.2021.00887 10.1146/annurev-bioeng-071516-044442 10.1145/3512527.3531392 10.1109/ICCVW54120.2021.00339 10.1109/CVPRW56347.2022.00324 10.1109/TPAMI.2021.3109287 10.1109/TCDS.2022.3193731 10.1016/j.media.2016.02.006 10.1109/CVPR42600.2020.00966 10.1016/j.ins.2023.119202 10.1016/j.cviu.2023.103747 10.1109/CVPR52688.2022.00784 10.1109/ICCVW54120.2021.00266 10.1109/TCSVT.2022.3179021 10.1109/CVPR52729.2023.02310 10.1371/journal.pone.0253415 10.1109/WACV48630.2021.00066 10.1109/TPAMI.2021.3103390 10.1109/CVPR52688.2022.00706 10.1109/TPAMI.2017.2773081 10.1109/CVPR.2016.308 10.1109/WACV57701.2024.00297 10.1109/CVPR46437.2021.00997 10.1145/3133956.3133982 10.1109/ICCV51070.2023.01377 10.1109/ICCV48922.2021.00885 10.1109/WACV56688.2023.00055 10.1109/TCSVT.2023.3234307 10.1109/ICCV51070.2023.00946 10.1109/TIP.2023.3258753 10.1109/ICCV.2019.00642 10.1109/CVPR.2017.572 10.1073/pnas.1611835114 10.1016/j.knosys.2022.109155 10.5244/C.35.324 10.1145/3474085.3475384 10.1007/s11390-021-1106-5 10.1109/TNNLS.2021.3111732 10.1109/WACV56688.2023.00416 10.1109/TNSRE.2022.3144169 10.1109/TIP.2021.3130530 10.1016/j.knosys.2023.111150 10.1016/j.jbi.2023.104404 10.1109/TII.2023.3297323 10.1016/j.media.2017.07.005 10.1109/TIP.2021.3112012 10.1109/ICCVW60793.2023.00466 10.1109/CVPR.2019.00503 10.1016/j.media.2022.102457 10.1109/TPAMI.2023.3270288 10.1109/TMI.2014.2377694 10.1109/WACV51458.2022.00115 10.3390/s22114238 10.1016/j.neunet.2023.08.005 10.1109/CVPR52688.2022.00707 10.1145/2939672.2939716 10.1109/WACV48630.2021.00052 10.1109/TIFS.2022.3149397 10.1109/WACV56688.2023.00052 10.1109/CVPR.2018.00392 10.1109/CVPR46437.2021.01361 10.1109/WACVW54805.2022.00027 10.18653/v1/2021.emnlp-main.20 10.1016/j.patcog.2021.108436 10.1109/CVPR.2019.00753 10.1145/3503161.3548009 10.1109/TMI.2022.3191535 10.1145/3469877.3490584 10.1109/CVPR52729.2023.01015 10.1109/TCSVT.2021.3111034 10.1016/j.media.2020.101907 10.1080/01621459.1986.10478240 10.1109/CVPR52688.2022.00816 10.1145/3503161.3548410 10.1109/TMM.2023.3321480 10.1109/ICCV.2013.208 10.1613/jair.1.12125 10.1561/2200000016 10.1109/TBME.2021.3117407 10.1109/ICCV48922.2021.00696 10.1016/j.neunet.2023.02.009 10.1109/ICCV48922.2021.00650 10.1109/CVPR46437.2021.00127 10.1109/TPAMI.2021.3128560 10.1016/j.media.2021.102136 10.1146/annurev.psych.56.091103.070217 10.1109/ICCV48922.2021.00888 10.1109/CVPR42600.2020.00874 10.1109/CVPR.2019.00309 10.1109/CVPR.2019.01053 10.1145/3447582 10.1109/CVPR.2018.00417 10.1109/TNNLS.2020.3017213 10.1109/TNNLS.2022.3160699 10.1109/WACV51458.2022.00286 10.1155/2018/7068349 10.1109/TNNLS.2020.2979670 10.1016/j.ymssp.2023.110159 10.1109/TIP.2022.3170728 10.1109/CVPR.2018.00395 10.1109/ICCV.2017.591 10.1109/TMI.2022.3150435 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Ltd Copyright © 2024 Elsevier Ltd. All rights reserved. |
| Copyright_xml | – notice: 2024 Elsevier Ltd – notice: Copyright © 2024 Elsevier Ltd. All rights reserved. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 5PM |
| DOI | 10.1016/j.neunet.2024.106230 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1879-2782 |
| EndPage | 106230 |
| ExternalDocumentID | PMC11015964 38490115 10_1016_j_neunet_2024_106230 S0893608024001540 |
| Genre | Systematic Review Journal Article |
| GrantInformation_xml | – fundername: NIA NIH HHS grantid: RF1 AG082938 – fundername: NIA NIH HHS grantid: RF1 AG073297 – fundername: NIBIB NIH HHS grantid: R01 EB035160 |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP CITATION EFKBS EFLBG ~HD AGCQF AGRNS BNPGV CGR CUY CVF ECM EIF NPM SSH 7X8 5PM |
| ID | FETCH-LOGICAL-c464t-c3f982ab73eaba5447f398a1a74492a6c686668b571e4c2e2e093faf3f002e6d3 |
| ISICitedReferencesCount | 64 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001216450500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0893-6080 1879-2782 |
| IngestDate | Tue Sep 30 17:04:32 EDT 2025 Thu Oct 02 10:35:35 EDT 2025 Sun Jul 13 01:33:08 EDT 2025 Sat Nov 29 07:19:09 EST 2025 Tue Nov 18 21:56:37 EST 2025 Sat Apr 13 16:40:05 EDT 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Domain adaptation Source-free Survey Unsupervised learning |
| Language | English |
| License | Copyright © 2024 Elsevier Ltd. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c464t-c3f982ab73eaba5447f398a1a74492a6c686668b571e4c2e2e093faf3f002e6d3 |
| Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Undefined-1 ObjectType-Feature-3 ObjectType-Review-4 content type line 23 |
| ORCID | 0000-0002-8769-496X |
| OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/11015964 |
| PMID | 38490115 |
| PQID | 2958299422 |
| PQPubID | 23479 |
| PageCount | 1 |
| ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_11015964 proquest_miscellaneous_2958299422 pubmed_primary_38490115 crossref_primary_10_1016_j_neunet_2024_106230 crossref_citationtrail_10_1016_j_neunet_2024_106230 elsevier_sciencedirect_doi_10_1016_j_neunet_2024_106230 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-06-01 |
| PublicationDateYYYYMMDD | 2024-06-01 |
| PublicationDate_xml | – month: 06 year: 2024 text: 2024-06-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Neural networks |
| PublicationTitleAlternate | Neural Netw |
| PublicationYear | 2024 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Eastwood, Mason, Williams, Schölkopf (b37) 2021 Li, Wang, Shi, Liu, Hou (b110) 2016 Tarvainen, Valpola (b185) 2017; 30 Karani, Erdil, Chaitanya, Konukoglu (b76) 2021; 68 (pp. 5018–5027). Xu, Yang, Cao, Wu, Wu, Li (b218) 2023; 33 (pp. 219–230). Qu, Liu, Zhu, Nie, Zhang (b157) 2024; 283 Hu, X., Zhang, K., Xia, L., Chen, A., Luo, J., Sun, Y., et al. (2024). ReCLIP: Refine contrastive language image pre-training with source free domain adaptation. In Kundu, Bhambri, Kulkarni, Sarkar, Jampani, Babu (b88) 2022 Kundu, J. N., Kulkarni, A., Singh, A., Jampani, V., & Babu, R. V. (2021). Generalize then adapt: Source-free domain adaptive semantic segmentation. In (pp. 10307–10317). Saenko, Kulis, Fritz, Darrell (b163) 2010 Liang, Hu, Feng (b116) 2020 (pp. 8715–8724). Huang, Y., Yang, X., Zhang, J., & Xu, C. (2022). Relative Alignment Network for Source-Free Multimodal Video Domain Adaptation. In Yu, Li, Du, Zhu, Shen (b244) 2023 Wang, Zhang, Yan, Shao, Li (b205) 2023 Fleuret, F., et al. (2021). Uncertainty reduction for model adaptation in semantic segmentation. In . Zhang, Ren, Feng, Yu, Beer, Liu (b249) 2023; 191 Chang, W. G., You, T., Seo, S., Kwak, S., & Han, B. (2019). Domain-specific batch normalization for unsupervised domain adaptation. In Gal, Hron, Kendall (b48) 2017; 30 Young, Hazarika, Poria, Cambria (b242) 2018; 13 Zhang, Cisse, Dauphin, Lopez-Paz (b247) 2017 Zhao, Feng, Li, Song, Liang, Chen (b254) 2023; 20 Yazdanpanah, M., & Moradi, P. (2022). Visual Domain Bridge: A Source-Free Domain Adaptation for Cross-Domain Few-Shot Learning. In Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., et al. (2017). Practical secure aggregation for privacy-preserving machine learning. In Liang, Hu, He, Feng (b119) 2021 Lopez-Paz, Ranzato (b132) 2017; 30 Arazo, Ortego, Albert, O’Connor, McGuinness (b5) 2019 Tang, Su, Chen, Ouyang (b182) 2021; vol. 35 Lee, Jung, Yim, Yoon (b96) 2022 (pp. 489–497). Caputo, Müller, Martinez-Gomez, Villegas, Acar, Patricia (b18) 2014 Litjens, Kooi, Bejnordi, Setio, Ciompi, Ghafoorian (b121) 2017; 42 Liu, Yoo, Xing, Kuo, El Fakhri, Kang (b125) 2022 Tian, Peng, Ma (b188) 2022; 14 VS, V., Oza, P., & Patel, V. M. (2023a). Instance relation graph guided source-free domain adaptive object detection. In Berthelot, Carlini, Goodfellow, Papernot, Oliver, Raffel (b12) 2019; 32 (pp. 3049–3059). Saito, Kim, Sclaroff, Saenko (b164) 2020; 33 Kang, G., Jiang, L., Yang, Y., & Hauptmann, A. G. (2019). Contrastive adaptation network for unsupervised domain adaptation. In Zhuang, Shen (b260) 2016; 31 Song, Chen, Ye, Song (b173) 2022; 31 Agarwal, P., Paudel, D. P., Zaech, J. N., & Van Gool, L. (2022). Unsupervised Robust Domain Adaptation without Source Data. In Arpit, Jastrzebski, Ballas, Krueger, Bengio, Kanwal (b6) 2017 Karim, N., Mithun, N. C., Rajvanshi, A., Chiu, H. p., Samarasekera, S., & Rahnavard, N. (2023). C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation. In (pp. 3723–3732). Raychaudhuri, D. S., Ta, C. K., Dutta, A., Lal, R., & Roy-Chowdhury, A. K. (2023). Prior-guided Source-free Domain Adaptation for Human Pose Estimation. In Deng, Dong, Socher, Li, Li, Fei-Fei (b30) 2009 Kemker, McClure, Abitino, Hayes, Kanan (b79) 2018; vol. 32 Liang, J., He, R., Sun, Z., & Tan, T. (2019). Distant supervised centroid shift: A simple and efficient approach to visual domain adaptation. In Han, Zhang, Wang, He, Su, Xi (b55) 2023; vol. 37 (pp. 474–483). Ding, Sheng, Liang, Zheng, He (b31) 2023; 167 Dong, Cong, Sun, Fang, Ding (b33) 2021; 46 Guan, Liu (b53) 2021; 69 Paul, Khurana, Aggarwal (b147) 2021 Nayak, Mopuri, Jain, Chakraborty (b143) 2021; 44 Xiao, Wei, Liu, Lin (b210) 2023 Hassaballah, Awad (b56) 2020 Luo, Chen, Tan, Li, He, Jia (b134) 2021 Hong, Zhang, Chen (b62) 2022 Li, D., Yang, Y., Song, Y. Z., & Hospedales, T. M. (2017). Deeper, broader and artier domain generalization. In (pp. 9010–9019). Lu, Sreekumar, Goodman, Banzhaf, Deb, Boddeti (b133) 2021; 43 Yang, Ma, Yuen (b226) 2022; 17 Peng, Huang, Zhu, Saenko (b151) 2019 (pp. 2818–2826). Kang, He, Luo, Fan, Liu, Yang (b74) 2022 Kirkpatrick, Pascanu, Rabinowitz, Veness, Desjardins, Rusu (b83) 2017; 114 Liu, Zhang, Wang, Wang (b130) 2021 (pp. 2868–2877). Song, Ma, Zhang, Zhang (b174) 2020; 8 Ba, Kiros, Hinton (b8) 2016 Wang, Liang, Zhang (b202) 2021 Lester, Al-Rfou, Constant (b99) 2021 (pp. 8344–8353). Liu, Li, An, Chen (b123) 2022 Bonawitz, Eichner, Grieskamp, Huba, Ingerman, Ivanov (b14) 2019; 1 Jing, Zhen, Li, Snoek (b73) 2022; 35 Jeon, Lee, Kang (b72) 2021; 16 Li, Chen, Luo, He, Tan (b101) 2022 (pp. 451–460). Chen, Lin, Yang, Xie, Pu, Zhuang (b23) 2022 Zara, G., Conti, A., Roy, S., Lathuilière, S., Rota, P., & Ricci, E. (2023). The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation. In Yang, Wang, Wang, Jui, van de Weijer (b231) 2022 Hou, Y., & Zheng, L. (2021). Visualizing adapted knowledge in domain transfer. In Yang, Tang, Zhong, Ding, Shao, Sebe (b228) 2021 (pp. 6645–6654). Roy, Trapp, Pilzer, Kannala, Sebe, Ricci (b162) 2022 Tanwisuth, Zhang, Zheng, He, Zhou (b184) 2023 Liu, Yuan (b127) 2022; 41 Liu, Y., Zhang, W., & Wang, J. (2021). Source-free domain adaptation for semantic segmentation. In Liu, Yoo, Xing, Kuo, El Fakhri, Kang (b126) 2022; vol. 12032 Ahmed, Lohit, Peng, Jones, Roy-Chowdhury (b3) 2022 Bochkovskiy, Wang, Liao (b13) 2020 Ding, N., Xu, Y., Tang, Y., Xu, C., Wang, Y., & Tao, D. (2022). Source-Free Domain Adaptation via Distribution Estimation. In Grandvalet, Bengio (b52) 2004; 17 Li, Du, Zhu, Ding, Lu, Shen (b104) 2021; 44 Liu, Chen, Dai, Gou, Huang, Xiong (b122) 2022 Shen, Bu, Wornell (b169) 2023 (pp. 3274–3283). Lee, C. Y., Batra, T., Baig, M. H., & Ulbricht, D. (2019). Sliced wasserstein discrepancy for unsupervised domain adaptation. In Boudiaf, M., Mueller, R., Ben Ayed, I., & Bertinetto, L. (2022). Parameter-free Online Test-time Adaptation. In Hegde, Sindagi, Kilic, Cooper, Foster, Patel (b60) 2021 (pp. 1406–1415). Dosovitskiy, Beyer, Kolesnikov, Weissenborn, Zhai, Unterthiner (b35) 2020 Huang, Guan, Xiao, Lu (b67) 2021; 34 Liang, Hu, Feng, He (b117) 2021 Lekhtman, E., Ziser, Y., & Reichart, R. (2021). DILBERT: Customized pre-training for domain adaptation with category shift, with an application to aspect extraction. In Hou, Zheng (b63) 2020 Kundu, J. N., Venkat, N., Babu, R. V., et al. (2020). Universal source-free domain adaptation. In Li, Sahu, Talwalkar, Smith (b109) 2020; 37 Müller, Kornblith, Hinton (b140) 2019; 32 Saito, K., & Saenko, K. (2021). OVANet: One-vs-all network for universal domain adaptation. In Xu, Lu, Wang, Luo, Jayender, Ma (b214) 2021 Kothandaraman, Shekhar, Sancheti, Ghuhan, Shukla, Manocha (b86) 2022 Liu, Xing, Yang, El Fakhri, Woo (b124) 2021 Ishii, Sugiyama (b70) 2021 Wang, Shelhamer, Liu, Olshausen, Darrell (b203) 2020 (pp. 444–454). Ye, M., Zhang, J., Ouyang, J., & Yuan, D. (2021). Source data-free unsupervised domain adaptation for semantic segmentation. In (pp. 8003–8013). (pp. 9000–9009). Yan, Guo (b220) 2022 Li, Zhou, Li, Wang, Bu, Yu (b114) 2023; 642 Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the Inception architecture for computer vision. In Yang, Peng, Wang, Zhu, Feng, Xie (b227) 2022 (pp. 1652–1660). VS, Valanarasu, Patel (b197) 2022 Lo, S. Y., Oza, P., Chennupati, S., Galindo, A., & Patel, V. M. (2023). Spatio-temporal pixel-level contrastive learning-based source-free domain adaptation for video semantic segmentation. In Yang, Chen, Jiang, Liu, Cao, Heng (b222) 2022; 41 (pp. 615–625). (pp. 10103–10112). Kundu, J. N., Venkat, N., Revanur, A., Babu, R. V., et al. (2020). Towards inheritable models for open-set domain adaptation. In Li, R., Jiao, Q., Cao, W., Wong, H.-S., & Wu, S. (2020). Model adaptation: Unsupervised domain adaptation without source data. In Yang, Kuo, Hsu (b225) 2022 Kendall, Gal (b80) 2017; 30 Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., & Wang, B. (2019). Moment matching for multi-source domain adaptation. In (pp. 7354–7362). (pp. 7046–7056). Qin, You, Wang, Kuo, Fu (b155) 2019; 32 Tang, Yang, Ma, Hendrich, Zeng, Ge (b183) 2021 Tierney, Kadane (b190) 1986; 81 Taufique, Jahan, Savakis (b186) 2021 (pp. 1424–1433). Fang, Wang, Potter, Liu (b42) 2022 Fang, C., Xu, Y., & Rockmore, D. N. (2013). Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias. In Liang, Hu, Wang, He, Feng (b120) 2021 Yang, Zhu, Chen, Yan, Zhang, Willis (b233) 2020 Sun, van Soest, Dumontier (b178) 2023 (pp. 6567–6576). Yang, van de Weijer, Herranz, Jui (b223) 2021; 34 Li, Wu (b111) 2023 (pp. 10534–10543). Peng, Usman, Kaushik, Hoffman, Wang, Saenko (b152) 2017 Ahmed, S. M., Raychaudhuri, D. S., Paul, S., Oymak, S., & Roy-Chowdhury, A. K. (2021). Unsupervised multi-source domain adaptation without access to source data. In (pp. 4544–4553). Pei, Jiang, Men, Chen, Liu, Chen (b148) 2023; 32 Luo, Wang, Chen, Huang, Baktashmotlagh (b135) 2023 Tan, Yu, Cui, Yang (b180) 2023; 34 Wang, Deng (b198) 2018; 312 Srivastava, Hinton, Krizhevsky, Sutskever, Salakhutdinov (b175) 2014; 15 Chen, Liu, Kira, Wang, Huang (b25) 2019 (pp. 7151–7160). Rao, Meng, Ding, Qi, Liu, Zhang (b159) 2023; 26 Zhang, D., Ye, M., Xiong, L., Li, S., & Li, X. (2021). Source-Style Transferred Mean Teacher for Source-data Free Object Detection. In Ioffe, Szegedy (b69) 2015 Xiong, Ye, Zhang, Gan, Liu (b212) 2022; 124 Gawlikowski, Tassi, Ali, Lee, Humt, Feng (b50) 2023 He, Carass, Zuo, Dewey, Prince (b57) 2020 Menze, Jakab, Bauer, Kalpathy-Cramer, Farahani, Kirby (b139) 2014; 34 (pp. 2347–2356). Kumar, V., Lal, R., Patil, H., & Chakraborty, A. (2023). Conmix for source-free single and multi-target domain adaptation. In Wistuba, Rawat, Pedapati (b207) 2019 Wang, Wu, Weng, Chen, Qi, Jiang (b204) 2022; 25 He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In Elsken, Metzen, Hutter (b38) 2019; 20 Klingner, M., Termöhlen, J.-A., Ritterbach, J., & Fingscheidt, T. (2022). Unsupervised batchnorm adaptation (UBNA): A domain adaptation method for s 10.1016/j.neunet.2024.106230_b200 Lee (10.1016/j.neunet.2024.106230_b96) 2022 Kundu (10.1016/j.neunet.2024.106230_b88) 2022 Li (10.1016/j.neunet.2024.106230_b111) 2023 Ding (10.1016/j.neunet.2024.106230_b31) 2023; 167 Otter (10.1016/j.neunet.2024.106230_b146) 2020; 32 Zhang (10.1016/j.neunet.2024.106230_b248) 2020 Boyd (10.1016/j.neunet.2024.106230_b17) 2011; 3 10.1016/j.neunet.2024.106230_b77 10.1016/j.neunet.2024.106230_b78 10.1016/j.neunet.2024.106230_b75 Müller (10.1016/j.neunet.2024.106230_b140) 2019; 32 Fan (10.1016/j.neunet.2024.106230_b40) 2022; 30 Li (10.1016/j.neunet.2024.106230_b114) 2023; 642 Tian (10.1016/j.neunet.2024.106230_b189) 2021; 32 Wang (10.1016/j.neunet.2024.106230_b201) 2022 Liu (10.1016/j.neunet.2024.106230_b123) 2022 Bochkovskiy (10.1016/j.neunet.2024.106230_b13) 2020 Shen (10.1016/j.neunet.2024.106230_b169) 2023 Tang (10.1016/j.neunet.2024.106230_b183) 2021 Tierney (10.1016/j.neunet.2024.106230_b190) 1986; 81 Deng (10.1016/j.neunet.2024.106230_b30) 2009 Ho (10.1016/j.neunet.2024.106230_b61) 2020; 33 10.1016/j.neunet.2024.106230_b87 10.1016/j.neunet.2024.106230_b84 10.1016/j.neunet.2024.106230_b85 Saltori (10.1016/j.neunet.2024.106230_b167) 2020 10.1016/j.neunet.2024.106230_b82 Xiong (10.1016/j.neunet.2024.106230_b212) 2022; 124 Yang (10.1016/j.neunet.2024.106230_b230) 2023 Liang (10.1016/j.neunet.2024.106230_b120) 2021 Liu (10.1016/j.neunet.2024.106230_b124) 2021 Tian (10.1016/j.neunet.2024.106230_b187) 2021; 36 Kothandaraman (10.1016/j.neunet.2024.106230_b86) 2022 Wang (10.1016/j.neunet.2024.106230_b202) 2021 10.1016/j.neunet.2024.106230_b59 Stan (10.1016/j.neunet.2024.106230_b177) 2021 Ma (10.1016/j.neunet.2024.106230_b137) 2022 Qiu (10.1016/j.neunet.2024.106230_b156) 2021 Ganin (10.1016/j.neunet.2024.106230_b49) 2015 Liang (10.1016/j.neunet.2024.106230_b117) 2021 Huang (10.1016/j.neunet.2024.106230_b67) 2021; 34 Shen (10.1016/j.neunet.2024.106230_b170) 2017; 19 Hegde (10.1016/j.neunet.2024.106230_b60) 2021 Kirkpatrick (10.1016/j.neunet.2024.106230_b83) 2017; 114 10.1016/j.neunet.2024.106230_b68 10.1016/j.neunet.2024.106230_b66 He (10.1016/j.neunet.2024.106230_b58) 2021; 72 10.1016/j.neunet.2024.106230_b64 Zhou (10.1016/j.neunet.2024.106230_b258) 2021; 30 Liu (10.1016/j.neunet.2024.106230_b130) 2021 Ahmed (10.1016/j.neunet.2024.106230_b3) 2022 10.1016/j.neunet.2024.106230_b246 10.1016/j.neunet.2024.106230_b129 Li (10.1016/j.neunet.2024.106230_b109) 2020; 37 Lester (10.1016/j.neunet.2024.106230_b99) 2021 10.1016/j.neunet.2024.106230_b240 10.1016/j.neunet.2024.106230_b243 Liang (10.1016/j.neunet.2024.106230_b119) 2021 Yang (10.1016/j.neunet.2024.106230_b223) 2021; 34 Dong (10.1016/j.neunet.2024.106230_b34) 2021; 34 Jing (10.1016/j.neunet.2024.106230_b73) 2022; 35 Gal (10.1016/j.neunet.2024.106230_b47) 2016 Liu (10.1016/j.neunet.2024.106230_b127) 2022; 41 Li (10.1016/j.neunet.2024.106230_b108) 2023 Zhuang (10.1016/j.neunet.2024.106230_b260) 2016; 31 Arazo (10.1016/j.neunet.2024.106230_b5) 2019 10.1016/j.neunet.2024.106230_b234 Kundu (10.1016/j.neunet.2024.106230_b89) 2022 Li (10.1016/j.neunet.2024.106230_b102) 2021; vol. 35 10.1016/j.neunet.2024.106230_b112 10.1016/j.neunet.2024.106230_b115 10.1016/j.neunet.2024.106230_b236 10.1016/j.neunet.2024.106230_b235 10.1016/j.neunet.2024.106230_b238 Zhang (10.1016/j.neunet.2024.106230_b251) 2023; 15 Ishii (10.1016/j.neunet.2024.106230_b70) 2021 10.1016/j.neunet.2024.106230_b237 Karani (10.1016/j.neunet.2024.106230_b76) 2021; 68 10.1016/j.neunet.2024.106230_b118 10.1016/j.neunet.2024.106230_b239 Peng (10.1016/j.neunet.2024.106230_b151) 2019 Sun (10.1016/j.neunet.2024.106230_b178) 2023 Voulodimos (10.1016/j.neunet.2024.106230_b193) 2018; 2018 Chen (10.1016/j.neunet.2024.106230_b23) 2022 Song (10.1016/j.neunet.2024.106230_b173) 2022; 31 He (10.1016/j.neunet.2024.106230_b57) 2020 Xu (10.1016/j.neunet.2024.106230_b217) 2022 Wang (10.1016/j.neunet.2024.106230_b204) 2022; 25 Fang (10.1016/j.neunet.2024.106230_b41) 2020; 32 Berthelot (10.1016/j.neunet.2024.106230_b12) 2019; 32 Peng (10.1016/j.neunet.2024.106230_b150) 2022 Menze (10.1016/j.neunet.2024.106230_b139) 2014; 34 Yu (10.1016/j.neunet.2024.106230_b245) 2023 Xiao (10.1016/j.neunet.2024.106230_b210) 2023 10.1016/j.neunet.2024.106230_b106 Hu (10.1016/j.neunet.2024.106230_b65) 2022; 54 Tan (10.1016/j.neunet.2024.106230_b180) 2023; 34 10.1016/j.neunet.2024.106230_b229 Yang (10.1016/j.neunet.2024.106230_b226) 2022; 17 10.1016/j.neunet.2024.106230_b221 Guan (10.1016/j.neunet.2024.106230_b53) 2021; 69 Yan (10.1016/j.neunet.2024.106230_b220) 2022 Arpit (10.1016/j.neunet.2024.106230_b6) 2017 10.1016/j.neunet.2024.106230_b98 10.1016/j.neunet.2024.106230_b95 Xu (10.1016/j.neunet.2024.106230_b219) 2022 Chen (10.1016/j.neunet.2024.106230_b24) 2021 Gawlikowski (10.1016/j.neunet.2024.106230_b50) 2023 10.1016/j.neunet.2024.106230_b93 10.1016/j.neunet.2024.106230_b91 10.1016/j.neunet.2024.106230_b92 10.1016/j.neunet.2024.106230_b90 Wistuba (10.1016/j.neunet.2024.106230_b207) 2019 Gong (10.1016/j.neunet.2024.106230_b51) 2012 Laine (10.1016/j.neunet.2024.106230_b94) 2016 10.1016/j.neunet.2024.106230_b213 Li (10.1016/j.neunet.2024.106230_b105) 2017; 40 Hassaballah (10.1016/j.neunet.2024.106230_b56) 2020 Roy (10.1016/j.neunet.2024.106230_b162) 2022 Yang (10.1016/j.neunet.2024.106230_b222) 2022; 41 De Lange (10.1016/j.neunet.2024.106230_b29) 2021; 44 Gal (10.1016/j.neunet.2024.106230_b48) 2017; 30 Chen (10.1016/j.neunet.2024.106230_b25) 2019 Taufique (10.1016/j.neunet.2024.106230_b186) 2021 Liu (10.1016/j.neunet.2024.106230_b128) 2021 10.1016/j.neunet.2024.106230_b209 Ren (10.1016/j.neunet.2024.106230_b161) 2021; 54 Saito (10.1016/j.neunet.2024.106230_b164) 2020; 33 Grandvalet (10.1016/j.neunet.2024.106230_b52) 2004; 17 Lu (10.1016/j.neunet.2024.106230_b133) 2021; 43 Tanwisuth (10.1016/j.neunet.2024.106230_b184) 2023 Bonawitz (10.1016/j.neunet.2024.106230_b14) 2019; 1 10.1016/j.neunet.2024.106230_b168 Faisal (10.1016/j.neunet.2024.106230_b39) 2022 Yu (10.1016/j.neunet.2024.106230_b244) 2023 Yang (10.1016/j.neunet.2024.106230_b225) 2022 10.1016/j.neunet.2024.106230_b160 Li (10.1016/j.neunet.2024.106230_b101) 2022 Peng (10.1016/j.neunet.2024.106230_b152) 2017 10.1016/j.neunet.2024.106230_b166 10.1016/j.neunet.2024.106230_b165 Chen (10.1016/j.neunet.2024.106230_b22) 2020 Radford (10.1016/j.neunet.2024.106230_b158) 2021 Guan (10.1016/j.neunet.2024.106230_b54) 2022 Liu (10.1016/j.neunet.2024.106230_b126) 2022; vol. 12032 Zhang (10.1016/j.neunet.2024.106230_b249) 2023; 191 Litjens (10.1016/j.neunet.2024.106230_b121) 2017; 42 Bateson (10.1016/j.neunet.2024.106230_b10) 2022; 82 Dosovitskiy (10.1016/j.neunet.2024.106230_b35) 2020 Sohn (10.1016/j.neunet.2024.106230_b172) 2016; 29 Ashby (10.1016/j.neunet.2024.106230_b7) 2005; 56 Qu (10.1016/j.neunet.2024.106230_b157) 2024; 283 Prabhu (10.1016/j.neunet.2024.106230_b153) 2021 Du (10.1016/j.neunet.2024.106230_b36) 2021 Hou (10.1016/j.neunet.2024.106230_b63) 2020 Qin (10.1016/j.neunet.2024.106230_b155) 2019; 32 10.1016/j.neunet.2024.106230_b149 Elsken (10.1016/j.neunet.2024.106230_b38) 2019; 20 Chen (10.1016/j.neunet.2024.106230_b27) 2020 Luo (10.1016/j.neunet.2024.106230_b135) 2023 Yang (10.1016/j.neunet.2024.106230_b232) 2021; 31 Tian (10.1016/j.neunet.2024.106230_b188) 2022; 14 Kendall (10.1016/j.neunet.2024.106230_b80) 2017; 30 You (10.1016/j.neunet.2024.106230_b241) 2021 Nayak (10.1016/j.neunet.2024.106230_b143) 2021; 44 Kemker (10.1016/j.neunet.2024.106230_b79) 2018; vol. 32 Dong (10.1016/j.neunet.2024.106230_b33) 2021; 46 Ulyanov (10.1016/j.neunet.2024.106230_b191) 2016 10.1016/j.neunet.2024.106230_b4 Li (10.1016/j.neunet.2024.106230_b104) 2021; 44 Li (10.1016/j.neunet.2024.106230_b113) 2023 Xu (10.1016/j.neunet.2024.106230_b216) 2022 10.1016/j.neunet.2024.106230_b2 Li (10.1016/j.neunet.2024.106230_b100) 2022 10.1016/j.neunet.2024.106230_b9 Zhang (10.1016/j.neunet.2024.106230_b253) 2021 Abusitta (10.1016/j.neunet.2024.106230_b1) 2021 Srivastava (10.1016/j.neunet.2024.106230_b175) 2014; 15 Yang (10.1016/j.neunet.2024.106230_b224) 2022; 79 Eastwood (10.1016/j.neunet.2024.106230_b37) 2021 Liang (10.1016/j.neunet.2024.106230_b116) 2020 Qin (10.1016/j.neunet.2024.106230_b154) 2022 Song (10.1016/j.neunet.2024.106230_b174) 2020; 8 Li (10.1016/j.neunet.2024.106230_b107) 2022 Chen (10.1016/j.neunet.2024.106230_b21) 2020 10.1016/j.neunet.2024.106230_b131 Wang (10.1016/j.neunet.2024.106230_b203) 2020 10.1016/j.neunet.2024.106230_b252 Tang (10.1016/j.neunet.2024.106230_b181) 2021 Xiong (10.1016/j.neunet.2024.106230_b211) 2021; 36 Pei (10.1016/j.neunet.2024.106230_b148) 2023; 32 Stan (10.1016/j.neunet.2024.106230_b176) 2021 Zhou (10.1016/j.neunet.2024.106230_b257) 2022; 45 Paul (10.1016/j.neunet.2024.106230_b147) 2021 Liu (10.1016/j.neunet.2024.106230_b125) 2022 Nasr (10.1016/j.neunet.2024.106230_b142) 2019 Xu (10.1016/j.neunet.2024.106230_b215) 2022 Jeon (10.1016/j.neunet.2024.106230_b72) 2021; 16 Xu (10.1016/j.neunet.2024.106230_b214) 2021 Tarvainen (10.1016/j.neunet.2024.106230_b185) 2017; 30 Feng (10.1016/j.neunet.2024.106230_b44) 2021; 34 10.1016/j.neunet.2024.106230_b28 Liu (10.1016/j.neunet.2024.106230_b122) 2022 Ma (10.1016/j.neunet.2024.106230_b136) 2021 Saenko (10.1016/j.neunet.2024.106230_b163) 2010 Wang (10.1016/j.neunet.2024.106230_b198) 2018; 312 10.1016/j.neunet.2024.106230_b32 Young (10.1016/j.neunet.2024.106230_b242) 2018; 13 Lopez-Paz (10.1016/j.neunet.2024.106230_b132) 2017; 30 Hong (10.1016/j.neunet.2024.106230_b62) 2022 Zhang (10.1016/j.neunet.2024.106230_b247) 2017 Zhao (10.1016/j.neunet.2024.106230_b255) 2022; 22 10.1016/j.neunet.2024.106230_b192 Kang (10.1016/j.neunet.2024.106230_b74) 2022 10.1016/j.neunet.2024.106230_b195 Yang (10.1016/j.neunet.2024.106230_b231) 2022 10.1016/j.neunet.2024.106230_b194 10.1016/j.neunet.2024.106230_b199 Wu (10.1016/j.neunet.2024.106230_b208) 2021 Tang (10.1016/j.neunet.2024.106230_b182) 2021; vol. 35 10.1016/j.neunet.2024.106230_b46 Wang (10.1016/j.neunet.2024.106230_b205) 2023 10.1016/j.neunet.2024.106230_b45 10.1016/j.neunet.2024.106230_b43 Ba (10.1016/j.neunet.2024.106230_b8) 2016 Li (10.1016/j.neunet.2024.106230_b103) 2022 Yang (10.1016/j.neunet.2024.106230_b227) 2022 Zhang (10.1016/j.neunet.2024.106230_b250) 2020 Ioffe (10.1016/j.neunet.2024.106230_b |
| References_xml | – reference: Yin, H., Molchanov, P., Alvarez, J. M., Li, Z., Mallya, A., Hoiem, D., et al. (2020). Dreaming to distill: Data-free knowledge transfer via DeepInversion. In – volume: 312 start-page: 135 year: 2018 end-page: 153 ident: b198 article-title: Deep visual domain adaptation: A survey publication-title: Neurocomputing – year: 2021 ident: b253 article-title: Unsupervised domain adaptation of black-box source models – start-page: 1180 year: 2015 end-page: 1189 ident: b49 article-title: Unsupervised domain adaptation by backpropagation publication-title: International Conference on Machine Learning – year: 2020 ident: b63 article-title: Source free domain adaptation with image translation – volume: 43 start-page: 2971 year: 2021 end-page: 2989 ident: b133 article-title: Neural architecture transfer publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – reference: Xia, H., Zhao, H., & Ding, Z. (2021). Adaptive adversarial network for source-free domain adaptation. In – start-page: 6028 year: 2020 end-page: 6039 ident: b116 article-title: Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation publication-title: International Conference on Machine Learning – year: 2022 ident: b100 article-title: Jacobian norm for unsupervised source-free domain adaptation – year: 2021 ident: b128 article-title: Graph consistency based mean-teaching for unsupervised domain adaptive person re-identification – year: 2021 ident: b141 article-title: Test-time adaptation to distribution shift by confidence maximization and input transformation – year: 2021 ident: b183 article-title: Nearest neighborhood-based deep clustering for source data-absent unsupervised domain adaptation – year: 2022 ident: b123 article-title: Source-free unsupervised domain adaptation for blind image quality assessment – reference: (pp. 4178–4188). – year: 2021 ident: b60 article-title: Uncertainty-aware mean teacher for source-free unsupervised domain adaptive 3D object detection – reference: Kothandaraman, D., Chandra, R., & Manocha, D. (2021). SS-SFDA: Self-supervised source-free domain adaptation for road segmentation in hazardous environments. In – volume: 81 start-page: 82 year: 1986 end-page: 86 ident: b190 article-title: Accurate approximations for posterior moments and marginal densities publication-title: Journal of the American Statistical Association – year: 2003 ident: b138 article-title: Information Theory, Inference and Learning Algorithms – year: 2021 ident: b134 article-title: Exploiting negative learning for implicit pseudo label rectification in source-free domain adaptive semantic segmentation – volume: 33 start-page: 3860 year: 2023 end-page: 3871 ident: b218 article-title: Multi-source video domain adaptation with temporal attentive moment alignment network publication-title: IEEE Transactions on Circuits and Systems for Video Technology – reference: (pp. 489–497). – reference: Lo, S. Y., Oza, P., Chennupati, S., Galindo, A., & Patel, V. M. (2023). Spatio-temporal pixel-level contrastive learning-based source-free domain adaptation for video semantic segmentation. In – volume: 167 start-page: 92 year: 2023 end-page: 103 ident: b31 article-title: ProxyMix: Proxy-based mixup training with label refinery for source-free domain adaptation publication-title: Neural Networks – volume: 42 start-page: 60 year: 2017 end-page: 88 ident: b121 article-title: A survey on deep learning in medical image analysis publication-title: Medical Image Analysis – reference: Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., et al. (2017). Practical secure aggregation for privacy-preserving machine learning. In – reference: (pp. 2994–3003). – volume: 30 year: 2017 ident: b48 article-title: Concrete dropout publication-title: Advances in Neural Information Processing Systems – reference: Yu, H., Huang, J., Liu, Y., Zhu, Q., Zhou, M., & Zhao, F. (2022). Source-Free Domain Adaptation for Real-World Image Dehazing. In – volume: 69 start-page: 1173 year: 2021 end-page: 1185 ident: b53 article-title: Domain adaptation for medical image analysis: A survey publication-title: IEEE Transactions on Biomedical Engineering – start-page: 549 year: 2021 end-page: 559 ident: b124 article-title: Adapting off-the-shelf source segmenter for target medical image segmentation publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – year: 2021 ident: b186 article-title: ConDA: Continual unsupervised domain adaptation – start-page: 341 year: 2022 ident: b125 article-title: Unsupervised black-box model domain adaptation for brain tumor segmentation publication-title: Frontiers in Neuroscience – volume: vol. 35 start-page: 2665 year: 2021 end-page: 2673 ident: b182 article-title: Gradient regularized contrastive learning for continual domain adaptation publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – volume: 70 start-page: 1373 year: 2021 end-page: 1411 ident: b145 article-title: Confident learning: Estimating uncertainty in dataset labels publication-title: Journal of Artificial Intelligence Research – reference: Liang, J., He, R., Sun, Z., & Tan, T. (2019). Distant supervised centroid shift: A simple and efficient approach to visual domain adaptation. In – reference: (pp. 210–220). – reference: (pp. 4893–4902). – reference: Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., & Wang, B. (2019). Moment matching for multi-source domain adaptation. In – year: 2023 ident: b184 article-title: POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models – year: 2022 ident: b74 article-title: Privacy-preserving federated adversarial domain adaptation over feature groups for interpretability publication-title: IEEE Transactions on Big Data – volume: 161 start-page: 682 year: 2023 end-page: 692 ident: b97 article-title: Feature alignment by uncertainty and self-training for source-free unsupervised domain adaptation publication-title: Neural Networks – start-page: 1050 year: 2016 end-page: 1059 ident: b47 article-title: Dropout as a bayesian approximation: Representing model uncertainty in deep learning publication-title: International Conference on Machine Learning – reference: Xu, R., Chen, Z., Zuo, W., Yan, J., & Lin, L. (2018). Deep cocktail network: Multi-source unsupervised domain adaptation with category shift. In – volume: 34 start-page: 3635 year: 2021 end-page: 3649 ident: b67 article-title: Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data publication-title: Advances in Neural Information Processing Systems – year: 2022 ident: b201 article-title: Active source free domain adaptation – year: 2021 ident: b119 article-title: Distill and fine-tune: Effective adaptation from a black-box source model – start-page: 2066 year: 2012 end-page: 2073 ident: b51 article-title: Geodesic flow kernel for unsupervised domain adaptation publication-title: 2012 IEEE/CVF Conference on Computer Vision and Pattern Recognition – year: 2019 ident: b207 article-title: A survey on neural architecture search – volume: 34 start-page: 29393 year: 2021 end-page: 29405 ident: b223 article-title: Exploiting the intrinsic neighborhood structure for source-free domain adaptation publication-title: Advances in Neural Information Processing Systems – volume: 32 start-page: 2033 year: 2023 end-page: 2048 ident: b148 article-title: Uncertainty-induced transferability representation for source-free unsupervised domain adaptation publication-title: IEEE Transactions on Image Processing – reference: Li, D., Yang, Y., Song, Y. Z., & Hospedales, T. M. (2017). Deeper, broader and artier domain generalization. In – year: 2021 ident: b202 article-title: Give me your trained model: Domain adaptive semantic segmentation without source data – reference: (pp. 10307–10317). – volume: 1 start-page: 374 year: 2019 end-page: 388 ident: b14 article-title: Towards federated learning at scale: System design publication-title: Proceedings of Machine Learning and Systems – start-page: 2681 year: 2023 end-page: 2686 ident: b210 article-title: Adversarially robust source-free domain adaptation with relaxed adversarial training publication-title: 2023 IEEE International Conference on Multimedia and Expo – year: 2022 ident: b220 article-title: Dual moving average pseudo-labeling for source-free inductive domain adaptation – reference: (pp. 9010–9019). – reference: (pp. 444–454). – year: 2021 ident: b70 article-title: Source-free domain adaptation via distributional alignment by matching batch normalization statistics – volume: 30 year: 2017 ident: b80 article-title: What uncertainties do we need in bayesian deep learning for computer vision? publication-title: Advances in Neural Information Processing Systems – volume: 13 start-page: 55 year: 2018 end-page: 75 ident: b242 article-title: Recent trends in deep learning based natural language processing publication-title: IEEE Computational Intelligence Magazine – reference: Kumar, V., Lal, R., Patil, H., & Chakraborty, A. (2023). Conmix for source-free single and multi-target domain adaptation. In – reference: (pp. 14996–15006). – year: 2021 ident: b228 article-title: Transformer-based source-free domain adaptation – volume: 15 year: 2023 ident: b251 article-title: Lightweight source-free transfer for privacy-preserving motor imagery classification publication-title: IEEE Transactions on Cognitive and Developmental Systems – start-page: 12365 year: 2022 end-page: 12377 ident: b96 article-title: Confidence score for source-free unsupervised domain adaptation publication-title: International Conference on Machine Learning – reference: Zara, G., Conti, A., Roy, S., Lathuilière, S., Rota, P., & Ricci, E. (2023). The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation. In – reference: (pp. 3964–3973). – year: 2023 ident: b244 article-title: A comprehensive survey on source-free domain adaptation – volume: 29 year: 2016 ident: b172 article-title: Improved deep metric learning with multi-class N-pair loss objective publication-title: Advances in Neural Information Processing Systems – reference: Chen, M. H., Kira, Z., AlRegib, G., Yoo, J., Chen, R., & Zheng, J. (2019). Temporal attentive alignment for large-scale video domain adaptation. In – reference: VS, V., Oza, P., & Patel, V. M. (2023a). Instance relation graph guided source-free domain adaptive object detection. In – volume: vol. 35 start-page: 8474 year: 2021 end-page: 8481 ident: b102 article-title: A free lunch for unsupervised domain adaptive object detection without source data publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – reference: (pp. 12376–12385). – reference: (pp. 6321–6330). – volume: 41 start-page: 1897 year: 2022 end-page: 1908 ident: b127 article-title: A source-free domain adaptive polyp detection framework with style diversification flow publication-title: IEEE Transactions on Medical Imaging – start-page: 30976 year: 2023 end-page: 30991 ident: b169 article-title: On balancing bias and variance in unsupervised multi-source-free domain adaptation publication-title: International Conference on Machine Learning – start-page: 3 year: 2023 end-page: 12 ident: b245 article-title: Source-free domain adaptation for medical image segmentation via prototype-anchored feature alignment and contrastive learning publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – reference: (pp. 474–483). – start-page: 147 year: 2022 end-page: 164 ident: b217 article-title: Source-free video domain adaptation by learning temporal consistency for action recognition publication-title: European Conference on Computer Vision – reference: Saito, K., & Saenko, K. (2021). OVANet: One-vs-all network for universal domain adaptation. In – reference: Boudiaf, M., Mueller, R., Ben Ayed, I., & Bertinetto, L. (2022). Parameter-free Online Test-time Adaptation. In – volume: 33 start-page: 6840 year: 2020 end-page: 6851 ident: b61 article-title: Denoising diffusion probabilistic models publication-title: Advances in Neural Information Processing Systems – start-page: 76 year: 2023 end-page: 80 ident: b113 article-title: Target-discriminability-induced multi-source-free domain adaptation publication-title: 2023 IEEE International Conference on Image Processing – reference: (pp. 4313–4322). – year: 2021 ident: b208 article-title: Domain adaptation without model transferring – year: 2021 ident: b156 article-title: Source-free domain adaptation via avatar prototype generation and adaptation – year: 2023 ident: b205 article-title: Black-box source-free domain adaptation via two-stage knowledge distillation – reference: (pp. 219–230). – volume: 34 start-page: 1993 year: 2014 end-page: 2024 ident: b139 article-title: The multimodal brain tumor image segmentation benchmark (BRATS) publication-title: IEEE Transactions on Medical Imaging – volume: 82 year: 2022 ident: b10 article-title: Source-free domain adaptation for image segmentation publication-title: Medical Image Analysis – start-page: 8748 year: 2021 end-page: 8763 ident: b158 article-title: Learning transferable visual models from natural language supervision publication-title: International Conference on Machine Learning – volume: 32 year: 2019 ident: b12 article-title: MixMatch: A holistic approach to semi-supervised learning publication-title: Advances in Neural Information Processing Systems – reference: Yeh, H. W., Meng, Q., & Harada, T. (2023). Misalignment-Free Relation Aggregation for Multi-Source-Free Domain Adaptation. In – reference: (pp. 10103–10112). – year: 2022 ident: b150 article-title: Toward better target representation for source-free and black-box domain adaptation – volume: 45 start-page: 4396 year: 2022 end-page: 4415 ident: b257 article-title: Domain generalization: A survey publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: vol. 37 start-page: 7811 year: 2023 end-page: 7820 ident: b55 article-title: Discriminability and transferability estimation: A Bayesian source importance estimation approach for multi-source-free domain adaptation publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – reference: (pp. 7046–7056). – reference: (pp. 478–488). – reference: (pp. 2818–2826). – volume: 34 start-page: 2427 year: 2021 end-page: 2440 ident: b71 article-title: Test-time classifier adjustment module for model-agnostic domain generalization publication-title: Advances in Neural Information Processing Systems – year: 2017 ident: b152 article-title: VisDA: The visual domain adaptation challenge – reference: Kundu, J. N., Kulkarni, A., Singh, A., Jampani, V., & Babu, R. V. (2021). Generalize then adapt: Source-free domain adaptive semantic segmentation. In – reference: Liu, Y., Zhang, W., & Wang, J. (2021). Source-free domain adaptation for semantic segmentation. In – volume: 44 start-page: 8196 year: 2021 end-page: 8211 ident: b104 article-title: Divergence-agnostic unsupervised domain adaptation by adversarial attacks publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 56 start-page: 149 year: 2005 end-page: 178 ident: b7 article-title: Human category learning publication-title: Annual Review of Psychology – reference: (pp. 9000–9009). – year: 2017 ident: b247 article-title: Mixup: Beyond empirical risk minimization – volume: 114 start-page: 3521 year: 2017 end-page: 3526 ident: b83 article-title: Overcoming catastrophic forgetting in neural networks publication-title: Proceedings of the National Academy of Sciences – start-page: 1091 year: 2022 end-page: 1095 ident: b101 article-title: Adaptive pseudo labeling for source-free domain adaptation in medical image segmentation publication-title: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing – year: 2021 ident: b147 article-title: Unsupervised adaptation of semantic segmentation models without source data – reference: Saito, K., Watanabe, K., Ushiku, Y., & Harada, T. (2018). Maximum classifier discrepancy for unsupervised domain adaptation. In – year: 2021 ident: b241 article-title: Test-time batch statistics calibration for covariate shift – reference: Ahmed, S. M., Raychaudhuri, D. S., Paul, S., Oymak, S., & Roy-Chowdhury, A. K. (2021). Unsupervised multi-source domain adaptation without access to source data. In – reference: Yazdanpanah, M., & Moradi, P. (2022). Visual Domain Bridge: A Source-Free Domain Adaptation for Cross-Domain Few-Shot Learning. In – volume: 36 start-page: 3746 year: 2021 end-page: 3766 ident: b211 article-title: Source data-free domain adaptation of object detector through domain-specific perturbation publication-title: International Journal of Intelligent Systems – year: 2020 ident: b56 article-title: Deep Learning in Computer Vision: Principles and Applications – volume: 17 year: 2004 ident: b52 article-title: Semi-supervised learning by entropy minimization publication-title: Advances in Neural Information Processing Systems – reference: (pp. 6567–6576). – volume: 32 year: 2019 ident: b259 article-title: Deep leakage from gradients publication-title: Advances in Neural Information Processing Systems – volume: 32 year: 2019 ident: b155 article-title: PointDAN: A multi-scale 3D domain adaption network for point cloud representation publication-title: Advances in Neural Information Processing Systems – volume: 44 start-page: 8465 year: 2021 end-page: 8481 ident: b143 article-title: Mining data impressions from deep models as substitute for the unavailable training data publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – year: 2019 ident: b25 article-title: A closer look at few-shot classification – start-page: 537 year: 2022 end-page: 555 ident: b162 article-title: Uncertainty-guided source-free domain adaptation publication-title: European Conference on Computer Vision – start-page: 490 year: 2020 end-page: 499 ident: b11 article-title: Source-relaxed domain adaptation for image segmentation publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – volume: 46 start-page: 1664 year: 2021 end-page: 1681 ident: b33 article-title: Where and how to transfer: Knowledge aggregation-induced transferability perception for unsupervised domain adaptation publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 31 start-page: 419 year: 2021 end-page: 432 ident: b232 article-title: Model-induced generalization error bound for information-theoretic representation learning in source-data-free unsupervised domain adaptation publication-title: IEEE Transactions on Image Processing – start-page: 1597 year: 2020 end-page: 1607 ident: b22 article-title: A simple framework for contrastive learning of visual representations publication-title: International Conference on Machine Learning – volume: 79 year: 2022 ident: b224 article-title: Source free domain adaptation for medical image segmentation with fourier style mining publication-title: Medical Image Analysis – start-page: 1 year: 2021 end-page: 6 ident: b1 article-title: VirtualGAN: Reducing mode collapse in generative adversarial networks using virtual mapping publication-title: 2021 International Joint Conference on Neural Networks – volume: 20 start-page: 1997 year: 2019 end-page: 2017 ident: b38 article-title: Neural architecture search: A survey publication-title: Journal of Machine Learning Research – start-page: 3576 year: 2022 end-page: 3579 ident: b216 article-title: Source-free domain adaptation for cross-scene hyperspectral image classification publication-title: IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium – year: 2023 ident: b178 article-title: Generating synthetic personal health data using conditional generative adversarial networks combining with differential privacy publication-title: Journal of Biomedical Informatics – year: 2022 ident: b103 article-title: Source-free domain adaptation for multi-site and lifespan brain skull stripping – volume: 8 start-page: 143233 year: 2020 end-page: 143240 ident: b174 article-title: Privacy-preserving unsupervised domain adaptation in federated setting publication-title: IEEE Access – year: 2022 ident: b42 article-title: Unsupervised cross-domain functional MRI adaptation for automated major depressive disorder identification publication-title: Medical Image Analysis – reference: Chidlovskii, B., Clinchant, S., & Csurka, G. (2016). Domain adaptation in the absence of source domain data. In – year: 2023 ident: b135 article-title: Source-free progressive graph learning for open-set domain adaptation publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 26 start-page: 4230 year: 2023 end-page: 4241 ident: b159 article-title: Parameter-efficient and student-friendly knowledge distillation publication-title: IEEE Transactions on Multimedia – start-page: 11710 year: 2022 end-page: 11728 ident: b89 article-title: Balancing discriminability and transferability for source-free domain adaptation publication-title: International Conference on Machine Learning – year: 2021 ident: b120 article-title: Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – reference: (pp. 7201–7211). – volume: 41 start-page: 3575 year: 2022 end-page: 3586 ident: b222 article-title: DLTTA: Dynamic learning rate for test-time adaptation on cross-domain medical images publication-title: IEEE Transactions on Medical Imaging – reference: Klingner, M., Termöhlen, J.-A., Ritterbach, J., & Fingscheidt, T. (2022). Unsupervised batchnorm adaptation (UBNA): A domain adaptation method for semantic segmentation without using source domain representations. In – reference: (pp. 7354–7362). – volume: 2018 year: 2018 ident: b193 article-title: Deep learning for computer vision: A brief review publication-title: Computational Intelligence and Neuroscience – start-page: 233 year: 2017 end-page: 242 ident: b6 article-title: A closer look at memorization in deep networks publication-title: International Conference on Machine Learning – volume: 22 start-page: 4238 year: 2022 ident: b255 article-title: Adaptive contrastive learning with label consistency for source data free unsupervised domain adaptation publication-title: Sensors – volume: 3 start-page: 1 year: 2011 end-page: 122 ident: b17 article-title: Distributed optimization and statistical learning via the alternating direction method of multipliers publication-title: Foundations and Trends® in Machine Learning – reference: Fang, C., Xu, Y., & Rockmore, D. N. (2013). Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias. In – reference: (pp. 8003–8013). – reference: . – reference: Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the Inception architecture for computer vision. In – year: 2022 ident: b62 article-title: Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation publication-title: Knowledge-Based Systems – start-page: 1 year: 2022 end-page: 10 ident: b39 article-title: Generating privacy preserving synthetic medical data publication-title: 2022 IEEE 9th International Conference on Data Science and Advanced Analytics – reference: (pp. 9729–9738). – reference: Chen, P., & Ma, A. J. (2022). Source-free Temporal Attentive Domain Adaptation for Video Action Recognition. In – volume: 36 start-page: 606 year: 2021 end-page: 616 ident: b187 article-title: Source-free unsupervised domain adaptation with sample transport learning publication-title: Journal of Computer Science and Technology – reference: (pp. 1175–1191). – volume: 20 start-page: 2787 year: 2023 end-page: 2798 ident: b254 article-title: Source-free domain adaptation for privacy-preserving seizure prediction publication-title: IEEE Transactions on Industrial Informatics – reference: Kang, G., Jiang, L., Yang, Y., & Hauptmann, A. G. (2019). Contrastive adaptation network for unsupervised domain adaptation. In – reference: Kurmi, V. K., Subramanian, V. K., & Namboodiri, V. P. (2021). Domain impression: A source data free domain adaptation method. In – reference: (pp. 10285–10295). – volume: 191 year: 2023 ident: b249 article-title: Universal source-free domain adaptation method for cross-domain fault diagnosis of machines publication-title: Mechanical Systems and Signal Processing – reference: Ke, Z., Wang, D., Yan, Q., Ren, J., & Lau, R. W. (2019). Dual student: Breaking the limits of the teacher in semi-supervised learning. In – volume: 124 year: 2022 ident: b212 article-title: Source data-free domain adaptation for a faster R-CNN publication-title: Pattern Recognition – reference: (pp. 6645–6654). – year: 2020 ident: b248 article-title: Unsupervised domain expansion from multiple sources – start-page: 430 year: 2020 end-page: 446 ident: b27 article-title: Unsupervised image classification for deep representation learning publication-title: European Conference on Computer Vision – year: 2021 ident: b136 article-title: Semi-supervised hypothesis transfer for source-free domain adaptation – year: 2016 ident: b8 article-title: Layer normalization – year: 2022 ident: b197 article-title: Target and task specific source-free domain adaptive image segmentation – start-page: 192 year: 2014 end-page: 211 ident: b18 article-title: ImageCLEF 2014: Overview and analysis of the results publication-title: International Conference of the Cross-Language Evaluation Forum for European Languages – volume: 17 start-page: 716 year: 2022 end-page: 731 ident: b226 article-title: Revealing task-relevant model memorization for source-protected unsupervised domain adaptation publication-title: IEEE Transactions on Information Forensics and Security – volume: 30 start-page: 8008 year: 2021 end-page: 8018 ident: b258 article-title: Domain adaptive ensemble learning publication-title: IEEE Transactions on Image Processing – reference: (pp. 8978–8987). – reference: Fleuret, F., et al. (2021). Uncertainty reduction for model adaptation in semantic segmentation. In – reference: Chang, W. G., You, T., Seo, S., Kwak, S., & Han, B. (2019). Domain-specific batch normalization for unsupervised domain adaptation. In – reference: (pp. 451–460). – start-page: 739 year: 2019 end-page: 753 ident: b142 article-title: Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning publication-title: 2019 IEEE Symposium on Security and Privacy – reference: Lekhtman, E., Ziser, Y., & Reichart, R. (2021). DILBERT: Customized pre-training for domain adaptation with category shift, with an application to aspect extraction. In – start-page: 1597 year: 2020 end-page: 1607 ident: b21 article-title: A simple framework for contrastive learning of visual representations publication-title: International Conference on Machine Learning – reference: (pp. 5018–5027). – year: 2020 ident: b35 article-title: An image is worth 16 – reference: Bang, D., & Shim, H. (2021). MGGAN: Solving mode collapse using manifold-guided training. In – reference: (pp. 8344–8353). – volume: 37 start-page: 50 year: 2020 end-page: 60 ident: b109 article-title: Federated learning: Challenges, methods, and future directions publication-title: IEEE Signal Processing Magazine – start-page: 511 year: 2022 end-page: 528 ident: b122 article-title: Source-free domain adaptation with contrastive domain alignment and self-supervised exploration for face anti-spoofing publication-title: European Conference on Computer Vision – volume: 32 year: 2019 ident: b140 article-title: When does label smoothing help? publication-title: Advances in Neural Information Processing Systems – year: 2021 ident: b153 article-title: S4T: Source-free domain adaptation for semantic segmentation via self-supervised selective self-training – reference: (pp. 3752–3761). – reference: (pp. 3274–3283). – volume: 14 start-page: 1 year: 2022 end-page: 17 ident: b188 article-title: Source-free unsupervised domain adaptation with trusted pseudo samples publication-title: ACM Transactions on Intelligent Systems and Technology – reference: Yan, H., Guo, Y., & Yang, C. (2021). Augmented self-labeling for source-free unsupervised domain adaptation. In – reference: He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In – reference: (pp. 9641–9650). – year: 2021 ident: b37 article-title: Source-free adaptation to measurement shift via bottom-up feature restoration – reference: (pp. 2009–2018). – reference: Venkateswara, H., Eusebio, J., Chakraborty, S., & Panchanathan, S. (2017). Deep hashing network for unsupervised domain adaptation. In – reference: (pp. 8715–8724). – volume: 40 start-page: 2935 year: 2017 end-page: 2947 ident: b105 article-title: Learning without forgetting publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: vol. 32 year: 2018 ident: b79 article-title: Measuring catastrophic forgetting in neural networks publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – volume: 19 start-page: 221 year: 2017 ident: b170 article-title: Deep learning in medical image analysis publication-title: Annual Review of Biomedical Engineering – year: 2020 ident: b203 article-title: Tent: Fully test-time adaptation by entropy minimization – reference: (pp. 24120–24131). – volume: 30 start-page: 205 year: 2022 end-page: 216 ident: b40 article-title: Unsupervised domain adaptation by statistics alignment for deep sleep staging networks publication-title: IEEE Transactions on Neural Systems and Rehabilitation Engineering – start-page: 1 year: 2020 end-page: 8 ident: b250 article-title: Discriminative joint probability maximum mean discrepancy (DJP-MMD) for domain adaptation publication-title: 2020 International Joint Conference on Neural Networks – start-page: 1 year: 2023 end-page: 8 ident: b111 article-title: Transformer-based multi-source domain adaptation without source data publication-title: 2023 International Joint Conference on Neural Networks – reference: Liang, J., Hu, D., Feng, J., & He, R. (2022). DINE: Domain adaptation from single and multiple black-box predictors. In – reference: (pp. 1424–1433). – year: 2022 ident: b219 article-title: EXTERN: Leveraging endo-temporal regularization for black-box video domain adaptation – reference: (pp. 9613–9623). – year: 2021 ident: b130 article-title: Data-free knowledge transfer: A survey – reference: Wang, Q., Fink, O., Van Gool, L., & Dai, D. (2022). Continual test-time domain adaptation. In – volume: 16 year: 2021 ident: b72 article-title: Unsupervised multi-source domain adaptation with no observable source data publication-title: PLoS One – volume: 15 start-page: 1929 year: 2014 end-page: 1958 ident: b175 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: Journal of Machine Learning Research – volume: 72 year: 2021 ident: b58 article-title: Autoencoder based self-supervised test-time adaptation for medical image analysis publication-title: Medical Image Analysis – reference: (pp. 7151–7160). – start-page: 3 year: 2021 end-page: 13 ident: b214 article-title: Noisy labels are treasure: Mean-teacher-assisted confident learning for hepatic vessel segmentation publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – reference: (pp. 5542–5550). – reference: (pp. 3049–3059). – volume: 34 start-page: 9587 year: 2023 end-page: 9603 ident: b180 article-title: Towards personalized federated learning publication-title: IEEE Transactions on Neural Networks and Learning Systems – reference: (pp. 1657–1664). – start-page: 771 year: 2020 end-page: 780 ident: b167 article-title: SF-UDA publication-title: 2020 International Conference on 3D Vision – start-page: 5679 year: 2021 end-page: 5685 ident: b181 article-title: Model adaptation through hypothesis transfer with gradual knowledge distillation publication-title: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems – volume: 30 year: 2017 ident: b132 article-title: Gradient episodic memory for continual learning publication-title: Advances in Neural Information Processing Systems – year: 2021 ident: b176 article-title: Privacy preserving domain adaptation for semantic segmentation of medical images – reference: (pp. 1652–1660). – year: 2022 ident: b54 article-title: Polycentric clustering and structural regularization for source-free unsupervised domain adaptation – reference: Kim, K., Ji, B., Yoon, D., & Hwang, S. (2021). Self-knowledge distillation with progressive refinement of targets. In – reference: (pp. 4544–4553). – reference: (pp. 1406–1415). – reference: (pp. 3520–3530). – reference: Ye, M., Zhang, J., Ouyang, J., & Yuan, D. (2021). Source data-free unsupervised domain adaptation for semantic segmentation. In – start-page: 177 year: 2022 end-page: 194 ident: b88 article-title: Concurrent subsidiary supervision for unsupervised source-free domain adaptation publication-title: European Conference on Computer Vision – start-page: 10185 year: 2022 end-page: 10192 ident: b23 article-title: Self-supervised noisy label learning for source-free unsupervised domain adaptation publication-title: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems – start-page: 1 year: 2023 end-page: 77 ident: b50 article-title: A survey of uncertainty in deep neural networks publication-title: Artificial Intelligence Review – start-page: 448 year: 2015 end-page: 456 ident: b69 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: International Conference on Machine Learning – volume: vol. 12032 start-page: 255 year: 2022 end-page: 260 ident: b126 article-title: Unsupervised domain adaptation for segmentation with black-box source model publication-title: Medical Imaging 2022: Image Processing – reference: Yao, H., Guo, Y., & Yang, C. (2021). Source-free unsupervised domain adaptation with surrogate data generation. In – volume: 32 start-page: 7019 year: 2022 end-page: 7032 ident: b256 article-title: Source-free open compound domain adaptation in semantic segmentation publication-title: IEEE Transactions on Circuits and Systems for Video Technology – reference: Huang, Y., Yang, X., Zhang, J., & Xu, C. (2022). Relative Alignment Network for Source-Free Multimodal Video Domain Adaptation. In – volume: 31 start-page: 3359 year: 2022 end-page: 3370 ident: b173 article-title: Spot-adaptive knowledge distillation publication-title: IEEE Transactions on Image Processing – reference: (pp. 615–625). – year: 2023 ident: b230 article-title: Casting a BAIT for offline and online source-free domain adaptation publication-title: Computer Vision and Image Understanding – volume: 68 year: 2021 ident: b76 article-title: Test-time adaptable neural networks for robust medical image segmentation publication-title: Medical Image Analysis – start-page: 214 year: 2022 end-page: 224 ident: b215 article-title: Denoising for relaxing: Unsupervised domain adaptive fundus image segmentation without source data publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 313 year: 2022 end-page: 323 ident: b137 article-title: Test-time adaptation with calibration of medical image classification nets for label distribution shift publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – reference: Yang, S., Wang, Y., van de Weijer, J., Herranz, L., & Jui, S. (2021). Generalized source-free domain adaptation. In – year: 2016 ident: b110 article-title: Revisiting batch normalization for practical domain adaptation – reference: Shenaj, D., Fanì, E., Toldo, M., Caldarola, D., Tavera, A., Michieli, U., et al. (2023). Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning. In – reference: Agarwal, P., Paudel, D. P., Zaech, J. N., & Van Gool, L. (2022). Unsupervised Robust Domain Adaptation without Source Data. In – volume: 2 start-page: 508 year: 2021 end-page: 518 ident: b81 article-title: Domain adaptation without source data publication-title: IEEE Transactions on Artificial Intelligence – volume: 30 year: 2017 ident: b185 article-title: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results publication-title: Advances in Neural Information Processing Systems – start-page: 213 year: 2010 end-page: 226 ident: b163 article-title: Adapting visual category models to new domains publication-title: European Conference on Computer Vision – start-page: 299 year: 2020 end-page: 315 ident: b233 article-title: MutualNet: Adaptive convnet via mutual learning from network width and resolution publication-title: European Conference on Computer Vision – reference: (pp. 13824–13833). – start-page: 140 year: 2018 end-page: 145 ident: b144 article-title: Source free domain adaptation using an off-the-shelf classifier publication-title: 2018 IEEE International Conference on Big Data (Big Data) – volume: 33 start-page: 16282 year: 2020 end-page: 16292 ident: b164 article-title: Universal domain adaptation through self supervision publication-title: Advances in Neural Information Processing Systems – start-page: 111 year: 2022 end-page: 127 ident: b3 article-title: Cross-modal knowledge transfer without task-relevant source data publication-title: European Conference on Computer Vision – volume: 34 start-page: 2848 year: 2021 end-page: 2860 ident: b34 article-title: Confident anchor-induced multi-source free domain adaptation publication-title: Advances in Neural Information Processing Systems – reference: Hou, Y., & Zheng, L. (2021). Visualizing adapted knowledge in domain transfer. In – year: 2021 ident: b99 article-title: The power of scale for parameter-efficient prompt tuning – reference: (pp. 1–8). – reference: (pp. 2868–2877). – reference: Kundu, J. N., Venkat, N., Babu, R. V., et al. (2020). Universal source-free domain adaptation. In – year: 2016 ident: b191 article-title: Instance normalization: The missing ingredient for fast stylization – volume: 32 start-page: 3749 year: 2021 end-page: 3760 ident: b189 article-title: VDM-DA: Virtual domain modeling for source data-free domain adaptation publication-title: IEEE Transactions on Circuits and Systems for Video Technology – volume: 54 start-page: 1 year: 2021 end-page: 34 ident: b161 article-title: A comprehensive survey of neural architecture search: Challenges and solutions publication-title: ACM Computing Surveys – volume: 25 start-page: 1665 year: 2022 end-page: 1673 ident: b204 article-title: Cross-domain contrastive learning for unsupervised domain adaptation publication-title: IEEE Transactions on Multimedia – year: 2021 ident: b206 article-title: Learning invariant representation with consistency and diversity for semi-supervised source hypothesis transfer – start-page: 1 year: 2022 end-page: 8 ident: b107 article-title: Source-free multi-domain adaptation with generally auxiliary model training publication-title: 2022 International Joint Conference on Neural Networks – start-page: 248 year: 2009 end-page: 255 ident: b30 article-title: ImageNet: A large-scale hierarchical image database publication-title: 2009 IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 32 start-page: 4309 year: 2020 end-page: 4322 ident: b41 article-title: Open set domain adaptation: Theoretical bound and algorithm publication-title: IEEE Transactions on Neural Networks and Learning Systems – year: 2016 ident: b94 article-title: Temporal ensembling for semi-supervised learning – year: 2023 ident: b108 article-title: Source-free multi-domain adaptation with fuzzy rule-based deep neural networks publication-title: IEEE Transactions on Fuzzy Systems – start-page: 3606 year: 2022 end-page: 3610 ident: b196 article-title: Mixture of teacher experts for source-free domain adaptive object detection publication-title: 2022 IEEE International Conference on Image Processing – volume: 642 year: 2023 ident: b114 article-title: Dynamic data-free knowledge distillation by easy-to-hard learning strategy publication-title: Information Sciences – reference: Yeh, H. W., Yang, B., Yuen, P. C., & Harada, T. (2021). SoFA: Source-data-free feature alignment for unsupervised domain adaptation. In – reference: Karim, N., Mithun, N. C., Rajvanshi, A., Chiu, H. p., Samarasekera, S., & Rahnavard, N. (2023). C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation. In – reference: Li, R., Jiao, Q., Cao, W., Wong, H.-S., & Wu, S. (2020). Model adaptation: Unsupervised domain adaptation without source data. In – year: 2021 ident: b36 article-title: Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation – volume: 54 start-page: 1 year: 2022 end-page: 37 ident: b65 article-title: Membership inference attacks on machine learning: A survey publication-title: ACM Computing Surveys – reference: Yao, C. H., Gong, B., Qi, H., Cui, Y., Zhu, Y., & Yang, M. H. (2022). Federated multi-target domain adaptation. In – reference: (pp. 6728–6736). – reference: (pp. 3723–3732). – volume: 283 year: 2024 ident: b157 article-title: Source-free style-diversity adversarial domain adaptation with privacy-preservation for person re-identification publication-title: Knowledge-Based Systems – start-page: 2593 year: 2021 end-page: 2601 ident: b177 article-title: Unsupervised model adaptation for continual semantic segmentation publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – reference: VS, V., Oza, P., & Patel, V. M. (2023b). Towards online domain adaptive object detection. In – volume: 31 start-page: 77 year: 2016 end-page: 87 ident: b260 article-title: Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI publication-title: Medical Image Analysis – year: 2022 ident: b227 article-title: Divide to adapt: Mitigating confirmation bias for domain adaptation of black-box predictors – volume: 34 start-page: 3082 year: 2021 end-page: 3096 ident: b44 article-title: Globally localized multisource domain adaptation for cross-domain fault diagnosis with category shift publication-title: IEEE Transactions on Neural Networks and Learning Systems – reference: Feng, H., You, Z., Chen, M., Zhang, T., Zhu, M., Wu, F., et al. (2021). KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation. In – start-page: 1 year: 2022 end-page: 15 ident: b154 article-title: Uncertainty-aware aggregation for federated open set domain adaptation publication-title: IEEE Transactions on Neural Networks and Learning Systems – reference: Sankaranarayanan, S., Balaji, Y., Jain, A., Lim, S. N., & Chellappa, R. (2018). Learning from synthetic data: Addressing domain shift for semantic segmentation. In – volume: 32 start-page: 604 year: 2020 end-page: 624 ident: b146 article-title: A survey of the usages of deep learning for natural language processing publication-title: IEEE Transactions on Neural Networks and Learning Systems – reference: Zhang, D., Ye, M., Xiong, L., Li, S., & Li, X. (2021). Source-Style Transferred Mean Teacher for Source-data Free Object Detection. In – reference: Wang, F., Han, Z., Gong, Y., & Yin, Y. (2022). Exploring Domain-Invariant Parameters for Source Free Domain Adaptation. In – reference: (pp. 2233–2242). – year: 2019 ident: b151 article-title: Federated adversarial domain adaptation – reference: (pp. 10534–10543). – year: 2020 ident: b13 article-title: YOLOv4: Optimal speed and accuracy of object detection – year: 2021 ident: b117 article-title: UMAD: Universal model adaptation under domain and category shift – reference: (pp. 1215–1224). – reference: (pp. 7212–7222). – year: 2022 ident: b231 article-title: Attracting and dispersing: A simple approach for source-free domain adaptation – start-page: 437 year: 2020 end-page: 446 ident: b57 article-title: Self domain adapted network publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – reference: Kundu, J. N., Venkat, N., Revanur, A., Babu, R. V., et al. (2020). Towards inheritable models for open-set domain adaptation. In – reference: Raychaudhuri, D. S., Ta, C. K., Dutta, A., Lal, R., & Roy-Chowdhury, A. K. (2023). Prior-guided Source-free Domain Adaptation for Human Pose Estimation. In – reference: Lee, C. Y., Batra, T., Baig, M. H., & Ulbricht, D. (2019). Sliced wasserstein discrepancy for unsupervised domain adaptation. In – volume: 35 start-page: 17173 year: 2022 end-page: 17187 ident: b73 article-title: Variational model perturbation for source-free domain adaptation publication-title: Advances in Neural Information Processing Systems – start-page: 225 year: 2021 end-page: 235 ident: b24 article-title: Source-free domain adaptive fundus image segmentation with denoised pseudo-labeling publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 1 year: 2022 end-page: 6 ident: b225 article-title: Source free domain adaptation for semantic segmentation via distribution transfer and adaptive class-balanced self-training publication-title: 2022 IEEE International Conference on Multimedia and Expo – start-page: 312 year: 2019 end-page: 321 ident: b5 article-title: Unsupervised label noise modeling and loss correction publication-title: International Conference on Machine Learning – year: 2022 ident: b86 article-title: DistillAdapt: Source-free active visual domain adaptation – reference: Ding, N., Xu, Y., Tang, Y., Xu, C., Wang, Y., & Tao, D. (2022). Source-Free Domain Adaptation via Distribution Estimation. In – reference: (pp. 2347–2356). – reference: (pp. 2975–2984). – volume: 44 start-page: 3366 year: 2021 end-page: 3385 ident: b29 article-title: A continual learning survey: Defying forgetting in classification tasks publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – reference: Hu, X., Zhang, K., Xia, L., Chen, A., Luo, J., Sun, Y., et al. (2024). ReCLIP: Refine contrastive language image pre-training with source free domain adaptation. In – volume: 30 year: 2017 ident: 10.1016/j.neunet.2024.106230_b132 article-title: Gradient episodic memory for continual learning publication-title: Advances in Neural Information Processing Systems – volume: 36 start-page: 3746 issue: 8 year: 2021 ident: 10.1016/j.neunet.2024.106230_b211 article-title: Source data-free domain adaptation of object detector through domain-specific perturbation publication-title: International Journal of Intelligent Systems doi: 10.1002/int.22434 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b156 – start-page: 549 year: 2021 ident: 10.1016/j.neunet.2024.106230_b124 article-title: Adapting off-the-shelf source segmenter for target medical image segmentation – volume: 54 start-page: 1 issue: 11s year: 2022 ident: 10.1016/j.neunet.2024.106230_b65 article-title: Membership inference attacks on machine learning: A survey publication-title: ACM Computing Surveys doi: 10.1145/3523273 – ident: 10.1016/j.neunet.2024.106230_b78 doi: 10.1109/ICCV.2019.00683 – ident: 10.1016/j.neunet.2024.106230_b194 doi: 10.1109/CVPR52729.2023.00343 – year: 2020 ident: 10.1016/j.neunet.2024.106230_b56 – start-page: 177 year: 2022 ident: 10.1016/j.neunet.2024.106230_b88 article-title: Concurrent subsidiary supervision for unsupervised source-free domain adaptation – ident: 10.1016/j.neunet.2024.106230_b200 doi: 10.1109/CVPR52688.2022.00701 – start-page: 8748 year: 2021 ident: 10.1016/j.neunet.2024.106230_b158 article-title: Learning transferable visual models from natural language supervision – volume: 8 start-page: 143233 year: 2020 ident: 10.1016/j.neunet.2024.106230_b174 article-title: Privacy-preserving unsupervised domain adaptation in federated setting publication-title: IEEE Access doi: 10.1109/ACCESS.2020.3014264 – start-page: 511 year: 2022 ident: 10.1016/j.neunet.2024.106230_b122 article-title: Source-free domain adaptation with contrastive domain alignment and self-supervised exploration for face anti-spoofing – volume: 43 start-page: 2971 issue: 9 year: 2021 ident: 10.1016/j.neunet.2024.106230_b133 article-title: Neural architecture transfer publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2021.3052758 – volume: 37 start-page: 50 issue: 3 year: 2020 ident: 10.1016/j.neunet.2024.106230_b109 article-title: Federated learning: Challenges, methods, and future directions publication-title: IEEE Signal Processing Magazine doi: 10.1109/MSP.2020.2975749 – volume: 82 year: 2022 ident: 10.1016/j.neunet.2024.106230_b10 article-title: Source-free domain adaptation for image segmentation publication-title: Medical Image Analysis doi: 10.1016/j.media.2022.102617 – volume: 13 start-page: 55 issue: 3 year: 2018 ident: 10.1016/j.neunet.2024.106230_b242 article-title: Recent trends in deep learning based natural language processing publication-title: IEEE Computational Intelligence Magazine doi: 10.1109/MCI.2018.2840738 – volume: 2 start-page: 508 issue: 6 year: 2021 ident: 10.1016/j.neunet.2024.106230_b81 article-title: Domain adaptation without source data publication-title: IEEE Transactions on Artificial Intelligence doi: 10.1109/TAI.2021.3110179 – start-page: 430 year: 2020 ident: 10.1016/j.neunet.2024.106230_b27 article-title: Unsupervised image classification for deep representation learning – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: 10.1016/j.neunet.2024.106230_b175 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: Journal of Machine Learning Research – volume: 312 start-page: 135 year: 2018 ident: 10.1016/j.neunet.2024.106230_b198 article-title: Deep visual domain adaptation: A survey publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.05.083 – ident: 10.1016/j.neunet.2024.106230_b149 doi: 10.1109/ICCV.2019.00149 – ident: 10.1016/j.neunet.2024.106230_b59 doi: 10.1109/CVPR42600.2020.00975 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b202 – year: 2016 ident: 10.1016/j.neunet.2024.106230_b8 – volume: 32 year: 2019 ident: 10.1016/j.neunet.2024.106230_b155 article-title: PointDAN: A multi-scale 3D domain adaption network for point cloud representation publication-title: Advances in Neural Information Processing Systems – volume: 25 start-page: 1665 year: 2022 ident: 10.1016/j.neunet.2024.106230_b204 article-title: Cross-domain contrastive learning for unsupervised domain adaptation publication-title: IEEE Transactions on Multimedia doi: 10.1109/TMM.2022.3146744 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b117 – ident: 10.1016/j.neunet.2024.106230_b165 doi: 10.1109/ICCV48922.2021.00887 – volume: 19 start-page: 221 year: 2017 ident: 10.1016/j.neunet.2024.106230_b170 article-title: Deep learning in medical image analysis publication-title: Annual Review of Biomedical Engineering doi: 10.1146/annurev-bioeng-071516-044442 – volume: 33 start-page: 6840 year: 2020 ident: 10.1016/j.neunet.2024.106230_b61 article-title: Denoising diffusion probabilistic models publication-title: Advances in Neural Information Processing Systems – ident: 10.1016/j.neunet.2024.106230_b26 doi: 10.1145/3512527.3531392 – ident: 10.1016/j.neunet.2024.106230_b85 doi: 10.1109/ICCVW54120.2021.00339 – ident: 10.1016/j.neunet.2024.106230_b236 doi: 10.1109/CVPRW56347.2022.00324 – volume: 44 start-page: 8196 issue: 11 year: 2021 ident: 10.1016/j.neunet.2024.106230_b104 article-title: Divergence-agnostic unsupervised domain adaptation by adversarial attacks publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2021.3109287 – volume: 15 issue: 2 year: 2023 ident: 10.1016/j.neunet.2024.106230_b251 article-title: Lightweight source-free transfer for privacy-preserving motor imagery classification publication-title: IEEE Transactions on Cognitive and Developmental Systems doi: 10.1109/TCDS.2022.3193731 – volume: 31 start-page: 77 year: 2016 ident: 10.1016/j.neunet.2024.106230_b260 article-title: Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI publication-title: Medical Image Analysis doi: 10.1016/j.media.2016.02.006 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b153 – ident: 10.1016/j.neunet.2024.106230_b106 doi: 10.1109/CVPR42600.2020.00966 – volume: 642 year: 2023 ident: 10.1016/j.neunet.2024.106230_b114 article-title: Dynamic data-free knowledge distillation by easy-to-hard learning strategy publication-title: Information Sciences doi: 10.1016/j.ins.2023.119202 – year: 2023 ident: 10.1016/j.neunet.2024.106230_b230 article-title: Casting a BAIT for offline and online source-free domain adaptation publication-title: Computer Vision and Image Understanding doi: 10.1016/j.cviu.2023.103747 – start-page: 1 year: 2023 ident: 10.1016/j.neunet.2024.106230_b50 article-title: A survey of uncertainty in deep neural networks publication-title: Artificial Intelligence Review – start-page: 12365 year: 2022 ident: 10.1016/j.neunet.2024.106230_b96 article-title: Confidence score for source-free unsupervised domain adaptation – start-page: 76 year: 2023 ident: 10.1016/j.neunet.2024.106230_b113 article-title: Target-discriminability-induced multi-source-free domain adaptation – volume: 32 year: 2019 ident: 10.1016/j.neunet.2024.106230_b140 article-title: When does label smoothing help? publication-title: Advances in Neural Information Processing Systems – ident: 10.1016/j.neunet.2024.106230_b118 doi: 10.1109/CVPR52688.2022.00784 – ident: 10.1016/j.neunet.2024.106230_b9 doi: 10.1109/ICCVW54120.2021.00266 – volume: 29 year: 2016 ident: 10.1016/j.neunet.2024.106230_b172 article-title: Improved deep metric learning with multi-class N-pair loss objective publication-title: Advances in Neural Information Processing Systems – volume: 32 start-page: 7019 issue: 10 year: 2022 ident: 10.1016/j.neunet.2024.106230_b256 article-title: Source-free open compound domain adaptation in semantic segmentation publication-title: IEEE Transactions on Circuits and Systems for Video Technology doi: 10.1109/TCSVT.2022.3179021 – ident: 10.1016/j.neunet.2024.106230_b77 doi: 10.1109/CVPR52729.2023.02310 – volume: 30 year: 2017 ident: 10.1016/j.neunet.2024.106230_b80 article-title: What uncertainties do we need in bayesian deep learning for computer vision? publication-title: Advances in Neural Information Processing Systems – volume: 16 issue: 7 year: 2021 ident: 10.1016/j.neunet.2024.106230_b72 article-title: Unsupervised multi-source domain adaptation with no observable source data publication-title: PLoS One doi: 10.1371/journal.pone.0253415 – ident: 10.1016/j.neunet.2024.106230_b93 doi: 10.1109/WACV48630.2021.00066 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b120 article-title: Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2021.3103390 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b136 – volume: 44 start-page: 8465 issue: 11 year: 2021 ident: 10.1016/j.neunet.2024.106230_b143 article-title: Mining data impressions from deep models as substitute for the unavailable training data publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – start-page: 225 year: 2021 ident: 10.1016/j.neunet.2024.106230_b24 article-title: Source-free domain adaptive fundus image segmentation with denoised pseudo-labeling – ident: 10.1016/j.neunet.2024.106230_b199 doi: 10.1109/CVPR52688.2022.00706 – year: 2019 ident: 10.1016/j.neunet.2024.106230_b207 – volume: 40 start-page: 2935 issue: 12 year: 2017 ident: 10.1016/j.neunet.2024.106230_b105 article-title: Learning without forgetting publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2017.2773081 – year: 2016 ident: 10.1016/j.neunet.2024.106230_b94 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b128 – volume: 34 start-page: 2427 year: 2021 ident: 10.1016/j.neunet.2024.106230_b71 article-title: Test-time classifier adjustment module for model-agnostic domain generalization publication-title: Advances in Neural Information Processing Systems – year: 2021 ident: 10.1016/j.neunet.2024.106230_b147 – start-page: 739 year: 2019 ident: 10.1016/j.neunet.2024.106230_b142 article-title: Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning – start-page: 1050 year: 2016 ident: 10.1016/j.neunet.2024.106230_b47 article-title: Dropout as a bayesian approximation: Representing model uncertainty in deep learning – year: 2003 ident: 10.1016/j.neunet.2024.106230_b138 – ident: 10.1016/j.neunet.2024.106230_b179 doi: 10.1109/CVPR.2016.308 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b119 – start-page: 192 year: 2014 ident: 10.1016/j.neunet.2024.106230_b18 article-title: ImageCLEF 2014: Overview and analysis of the results – ident: 10.1016/j.neunet.2024.106230_b66 doi: 10.1109/WACV57701.2024.00297 – start-page: 214 year: 2022 ident: 10.1016/j.neunet.2024.106230_b215 article-title: Denoising for relaxing: Unsupervised domain adaptive fundus image segmentation without source data – year: 2021 ident: 10.1016/j.neunet.2024.106230_b130 – start-page: 3 year: 2021 ident: 10.1016/j.neunet.2024.106230_b214 article-title: Noisy labels are treasure: Mean-teacher-assisted confident learning for hepatic vessel segmentation – start-page: 313 year: 2022 ident: 10.1016/j.neunet.2024.106230_b137 article-title: Test-time adaptation with calibration of medical image classification nets for label distribution shift – ident: 10.1016/j.neunet.2024.106230_b4 doi: 10.1109/CVPR46437.2021.00997 – ident: 10.1016/j.neunet.2024.106230_b15 doi: 10.1145/3133956.3133982 – ident: 10.1016/j.neunet.2024.106230_b160 doi: 10.1109/ICCV51070.2023.01377 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b54 – start-page: 771 year: 2020 ident: 10.1016/j.neunet.2024.106230_b167 article-title: SF-UDA3D: Source-free unsupervised domain adaptation for LiDAR-based 3D object detection – year: 2021 ident: 10.1016/j.neunet.2024.106230_b60 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b253 – ident: 10.1016/j.neunet.2024.106230_b229 doi: 10.1109/ICCV48922.2021.00885 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b197 – volume: 34 start-page: 29393 year: 2021 ident: 10.1016/j.neunet.2024.106230_b223 article-title: Exploiting the intrinsic neighborhood structure for source-free domain adaptation publication-title: Advances in Neural Information Processing Systems – start-page: 1597 year: 2020 ident: 10.1016/j.neunet.2024.106230_b21 article-title: A simple framework for contrastive learning of visual representations – start-page: 10185 year: 2022 ident: 10.1016/j.neunet.2024.106230_b23 article-title: Self-supervised noisy label learning for source-free unsupervised domain adaptation – ident: 10.1016/j.neunet.2024.106230_b195 doi: 10.1109/WACV56688.2023.00055 – volume: 33 start-page: 3860 issue: 8 year: 2023 ident: 10.1016/j.neunet.2024.106230_b218 article-title: Multi-source video domain adaptation with temporal attentive moment alignment network publication-title: IEEE Transactions on Circuits and Systems for Video Technology doi: 10.1109/TCSVT.2023.3234307 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b70 – ident: 10.1016/j.neunet.2024.106230_b246 doi: 10.1109/ICCV51070.2023.00946 – volume: 32 start-page: 2033 year: 2023 ident: 10.1016/j.neunet.2024.106230_b148 article-title: Uncertainty-induced transferability representation for source-free unsupervised domain adaptation publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2023.3258753 – start-page: 312 year: 2019 ident: 10.1016/j.neunet.2024.106230_b5 article-title: Unsupervised label noise modeling and loss correction – ident: 10.1016/j.neunet.2024.106230_b20 doi: 10.1109/ICCV.2019.00642 – year: 2017 ident: 10.1016/j.neunet.2024.106230_b247 – ident: 10.1016/j.neunet.2024.106230_b192 doi: 10.1109/CVPR.2017.572 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b150 – start-page: 1 year: 2023 ident: 10.1016/j.neunet.2024.106230_b111 article-title: Transformer-based multi-source domain adaptation without source data – year: 2021 ident: 10.1016/j.neunet.2024.106230_b37 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b220 – year: 2020 ident: 10.1016/j.neunet.2024.106230_b13 – volume: 114 start-page: 3521 issue: 13 year: 2017 ident: 10.1016/j.neunet.2024.106230_b83 article-title: Overcoming catastrophic forgetting in neural networks publication-title: Proceedings of the National Academy of Sciences doi: 10.1073/pnas.1611835114 – start-page: 213 year: 2010 ident: 10.1016/j.neunet.2024.106230_b163 article-title: Adapting visual category models to new domains – year: 2021 ident: 10.1016/j.neunet.2024.106230_b208 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b62 article-title: Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation publication-title: Knowledge-Based Systems doi: 10.1016/j.knosys.2022.109155 – year: 2019 ident: 10.1016/j.neunet.2024.106230_b25 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b176 – ident: 10.1016/j.neunet.2024.106230_b221 doi: 10.5244/C.35.324 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b227 – ident: 10.1016/j.neunet.2024.106230_b237 doi: 10.1145/3474085.3475384 – start-page: 140 year: 2018 ident: 10.1016/j.neunet.2024.106230_b144 article-title: Source free domain adaptation using an off-the-shelf classifier – volume: 36 start-page: 606 issue: 3 year: 2021 ident: 10.1016/j.neunet.2024.106230_b187 article-title: Source-free unsupervised domain adaptation with sample transport learning publication-title: Journal of Computer Science and Technology doi: 10.1007/s11390-021-1106-5 – start-page: 3 year: 2023 ident: 10.1016/j.neunet.2024.106230_b245 article-title: Source-free domain adaptation for medical image segmentation via prototype-anchored feature alignment and contrastive learning – start-page: 2593 year: 2021 ident: 10.1016/j.neunet.2024.106230_b177 article-title: Unsupervised model adaptation for continual semantic segmentation – volume: 34 start-page: 3082 issue: 6 year: 2021 ident: 10.1016/j.neunet.2024.106230_b44 article-title: Globally localized multisource domain adaptation for cross-domain fault diagnosis with category shift publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2021.3111732 – year: 2023 ident: 10.1016/j.neunet.2024.106230_b108 article-title: Source-free multi-domain adaptation with fuzzy rule-based deep neural networks publication-title: IEEE Transactions on Fuzzy Systems – ident: 10.1016/j.neunet.2024.106230_b87 doi: 10.1109/WACV56688.2023.00416 – start-page: 537 year: 2022 ident: 10.1016/j.neunet.2024.106230_b162 article-title: Uncertainty-guided source-free domain adaptation – volume: 30 start-page: 205 year: 2022 ident: 10.1016/j.neunet.2024.106230_b40 article-title: Unsupervised domain adaptation by statistics alignment for deep sleep staging networks publication-title: IEEE Transactions on Neural Systems and Rehabilitation Engineering doi: 10.1109/TNSRE.2022.3144169 – volume: 30 year: 2017 ident: 10.1016/j.neunet.2024.106230_b185 article-title: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results publication-title: Advances in Neural Information Processing Systems – year: 2023 ident: 10.1016/j.neunet.2024.106230_b184 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b201 – volume: 31 start-page: 419 year: 2021 ident: 10.1016/j.neunet.2024.106230_b232 article-title: Model-induced generalization error bound for information-theoretic representation learning in source-data-free unsupervised domain adaptation publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2021.3130530 – start-page: 147 year: 2022 ident: 10.1016/j.neunet.2024.106230_b217 article-title: Source-free video domain adaptation by learning temporal consistency for action recognition – volume: 283 year: 2024 ident: 10.1016/j.neunet.2024.106230_b157 article-title: Source-free style-diversity adversarial domain adaptation with privacy-preservation for person re-identification publication-title: Knowledge-Based Systems doi: 10.1016/j.knosys.2023.111150 – year: 2023 ident: 10.1016/j.neunet.2024.106230_b178 article-title: Generating synthetic personal health data using conditional generative adversarial networks combining with differential privacy publication-title: Journal of Biomedical Informatics doi: 10.1016/j.jbi.2023.104404 – volume: 20 start-page: 2787 issue: 2 year: 2023 ident: 10.1016/j.neunet.2024.106230_b254 article-title: Source-free domain adaptation for privacy-preserving seizure prediction publication-title: IEEE Transactions on Industrial Informatics doi: 10.1109/TII.2023.3297323 – start-page: 3576 year: 2022 ident: 10.1016/j.neunet.2024.106230_b216 article-title: Source-free domain adaptation for cross-scene hyperspectral image classification – volume: 42 start-page: 60 year: 2017 ident: 10.1016/j.neunet.2024.106230_b121 article-title: A survey on deep learning in medical image analysis publication-title: Medical Image Analysis doi: 10.1016/j.media.2017.07.005 – volume: 30 start-page: 8008 year: 2021 ident: 10.1016/j.neunet.2024.106230_b258 article-title: Domain adaptive ensemble learning publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2021.3112012 – start-page: 341 year: 2022 ident: 10.1016/j.neunet.2024.106230_b125 article-title: Unsupervised black-box model domain adaptation for brain tumor segmentation publication-title: Frontiers in Neuroscience – year: 2021 ident: 10.1016/j.neunet.2024.106230_b141 – volume: vol. 37 start-page: 7811 year: 2023 ident: 10.1016/j.neunet.2024.106230_b55 article-title: Discriminability and transferability estimation: A Bayesian source importance estimation approach for multi-source-free domain adaptation – ident: 10.1016/j.neunet.2024.106230_b238 doi: 10.1109/ICCVW60793.2023.00466 – ident: 10.1016/j.neunet.2024.106230_b75 doi: 10.1109/CVPR.2019.00503 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b228 – ident: 10.1016/j.neunet.2024.106230_b91 – volume: vol. 12032 start-page: 255 year: 2022 ident: 10.1016/j.neunet.2024.106230_b126 article-title: Unsupervised domain adaptation for segmentation with black-box source model – volume: 1 start-page: 374 year: 2019 ident: 10.1016/j.neunet.2024.106230_b14 article-title: Towards federated learning at scale: System design publication-title: Proceedings of Machine Learning and Systems – year: 2021 ident: 10.1016/j.neunet.2024.106230_b241 – start-page: 437 year: 2020 ident: 10.1016/j.neunet.2024.106230_b57 article-title: Self domain adapted network – start-page: 3606 year: 2022 ident: 10.1016/j.neunet.2024.106230_b196 article-title: Mixture of teacher experts for source-free domain adaptive object detection – volume: 79 year: 2022 ident: 10.1016/j.neunet.2024.106230_b224 article-title: Source free domain adaptation for medical image segmentation with fourier style mining publication-title: Medical Image Analysis doi: 10.1016/j.media.2022.102457 – start-page: 1 year: 2022 ident: 10.1016/j.neunet.2024.106230_b225 article-title: Source free domain adaptation for semantic segmentation via distribution transfer and adaptive class-balanced self-training – start-page: 2066 year: 2012 ident: 10.1016/j.neunet.2024.106230_b51 article-title: Geodesic flow kernel for unsupervised domain adaptation – year: 2023 ident: 10.1016/j.neunet.2024.106230_b135 article-title: Source-free progressive graph learning for open-set domain adaptation publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2023.3270288 – volume: 34 start-page: 1993 issue: 10 year: 2014 ident: 10.1016/j.neunet.2024.106230_b139 article-title: The multimodal brain tumor image segmentation benchmark (BRATS) publication-title: IEEE Transactions on Medical Imaging doi: 10.1109/TMI.2014.2377694 – volume: vol. 35 start-page: 2665 year: 2021 ident: 10.1016/j.neunet.2024.106230_b182 article-title: Gradient regularized contrastive learning for continual domain adaptation – start-page: 490 year: 2020 ident: 10.1016/j.neunet.2024.106230_b11 article-title: Source-relaxed domain adaptation for image segmentation – year: 2016 ident: 10.1016/j.neunet.2024.106230_b191 – ident: 10.1016/j.neunet.2024.106230_b234 doi: 10.1109/WACV51458.2022.00115 – year: 2020 ident: 10.1016/j.neunet.2024.106230_b248 – start-page: 5679 year: 2021 ident: 10.1016/j.neunet.2024.106230_b181 article-title: Model adaptation through hypothesis transfer with gradual knowledge distillation – volume: 22 start-page: 4238 issue: 11 year: 2022 ident: 10.1016/j.neunet.2024.106230_b255 article-title: Adaptive contrastive learning with label consistency for source data free unsupervised domain adaptation publication-title: Sensors doi: 10.3390/s22114238 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b186 – volume: 34 start-page: 2848 year: 2021 ident: 10.1016/j.neunet.2024.106230_b34 article-title: Confident anchor-induced multi-source free domain adaptation publication-title: Advances in Neural Information Processing Systems – year: 2022 ident: 10.1016/j.neunet.2024.106230_b74 article-title: Privacy-preserving federated adversarial domain adaptation over feature groups for interpretability publication-title: IEEE Transactions on Big Data – start-page: 11710 year: 2022 ident: 10.1016/j.neunet.2024.106230_b89 article-title: Balancing discriminability and transferability for source-free domain adaptation – volume: 167 start-page: 92 year: 2023 ident: 10.1016/j.neunet.2024.106230_b31 article-title: ProxyMix: Proxy-based mixup training with label refinery for source-free domain adaptation publication-title: Neural Networks doi: 10.1016/j.neunet.2023.08.005 – ident: 10.1016/j.neunet.2024.106230_b32 doi: 10.1109/CVPR52688.2022.00707 – volume: 35 start-page: 17173 year: 2022 ident: 10.1016/j.neunet.2024.106230_b73 article-title: Variational model perturbation for source-free domain adaptation publication-title: Advances in Neural Information Processing Systems – year: 2021 ident: 10.1016/j.neunet.2024.106230_b99 – ident: 10.1016/j.neunet.2024.106230_b28 doi: 10.1145/2939672.2939716 – volume: vol. 32 year: 2018 ident: 10.1016/j.neunet.2024.106230_b79 article-title: Measuring catastrophic forgetting in neural networks – ident: 10.1016/j.neunet.2024.106230_b239 doi: 10.1109/WACV48630.2021.00052 – start-page: 299 year: 2020 ident: 10.1016/j.neunet.2024.106230_b233 article-title: MutualNet: Adaptive convnet via mutual learning from network width and resolution – volume: 17 start-page: 716 year: 2022 ident: 10.1016/j.neunet.2024.106230_b226 article-title: Revealing task-relevant model memorization for source-protected unsupervised domain adaptation publication-title: IEEE Transactions on Information Forensics and Security doi: 10.1109/TIFS.2022.3149397 – start-page: 1597 year: 2020 ident: 10.1016/j.neunet.2024.106230_b22 article-title: A simple framework for contrastive learning of visual representations – volume: 17 year: 2004 ident: 10.1016/j.neunet.2024.106230_b52 article-title: Semi-supervised learning by entropy minimization publication-title: Advances in Neural Information Processing Systems – volume: vol. 35 start-page: 8474 year: 2021 ident: 10.1016/j.neunet.2024.106230_b102 article-title: A free lunch for unsupervised domain adaptive object detection without source data – ident: 10.1016/j.neunet.2024.106230_b45 – ident: 10.1016/j.neunet.2024.106230_b171 doi: 10.1109/WACV56688.2023.00052 – year: 2020 ident: 10.1016/j.neunet.2024.106230_b203 – start-page: 6028 year: 2020 ident: 10.1016/j.neunet.2024.106230_b116 article-title: Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation – ident: 10.1016/j.neunet.2024.106230_b166 doi: 10.1109/CVPR.2018.00392 – volume: 44 start-page: 3366 issue: 7 year: 2021 ident: 10.1016/j.neunet.2024.106230_b29 article-title: A continual learning survey: Defying forgetting in classification tasks publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – ident: 10.1016/j.neunet.2024.106230_b64 doi: 10.1109/CVPR46437.2021.01361 – ident: 10.1016/j.neunet.2024.106230_b84 doi: 10.1109/WACVW54805.2022.00027 – start-page: 233 year: 2017 ident: 10.1016/j.neunet.2024.106230_b6 article-title: A closer look at memorization in deep networks – ident: 10.1016/j.neunet.2024.106230_b98 doi: 10.18653/v1/2021.emnlp-main.20 – volume: 14 start-page: 1 issue: 2 year: 2022 ident: 10.1016/j.neunet.2024.106230_b188 article-title: Source-free unsupervised domain adaptation with trusted pseudo samples publication-title: ACM Transactions on Intelligent Systems and Technology – volume: 124 year: 2022 ident: 10.1016/j.neunet.2024.106230_b212 article-title: Source data-free domain adaptation for a faster R-CNN publication-title: Pattern Recognition doi: 10.1016/j.patcog.2021.108436 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b183 – ident: 10.1016/j.neunet.2024.106230_b19 doi: 10.1109/CVPR.2019.00753 – ident: 10.1016/j.neunet.2024.106230_b68 doi: 10.1145/3503161.3548009 – volume: 30 year: 2017 ident: 10.1016/j.neunet.2024.106230_b48 article-title: Concrete dropout publication-title: Advances in Neural Information Processing Systems – volume: 32 year: 2019 ident: 10.1016/j.neunet.2024.106230_b259 article-title: Deep leakage from gradients publication-title: Advances in Neural Information Processing Systems – volume: 34 start-page: 3635 year: 2021 ident: 10.1016/j.neunet.2024.106230_b67 article-title: Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data publication-title: Advances in Neural Information Processing Systems – year: 2021 ident: 10.1016/j.neunet.2024.106230_b134 – volume: 41 start-page: 3575 issue: 12 year: 2022 ident: 10.1016/j.neunet.2024.106230_b222 article-title: DLTTA: Dynamic learning rate for test-time adaptation on cross-domain medical images publication-title: IEEE Transactions on Medical Imaging doi: 10.1109/TMI.2022.3191535 – ident: 10.1016/j.neunet.2024.106230_b252 doi: 10.1145/3469877.3490584 – year: 2023 ident: 10.1016/j.neunet.2024.106230_b205 – ident: 10.1016/j.neunet.2024.106230_b131 doi: 10.1109/CVPR52729.2023.01015 – start-page: 1 year: 2022 ident: 10.1016/j.neunet.2024.106230_b154 article-title: Uncertainty-aware aggregation for federated open set domain adaptation publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 32 start-page: 3749 issue: 6 year: 2021 ident: 10.1016/j.neunet.2024.106230_b189 article-title: VDM-DA: Virtual domain modeling for source data-free domain adaptation publication-title: IEEE Transactions on Circuits and Systems for Video Technology doi: 10.1109/TCSVT.2021.3111034 – start-page: 1 year: 2022 ident: 10.1016/j.neunet.2024.106230_b107 article-title: Source-free multi-domain adaptation with generally auxiliary model training – volume: 68 year: 2021 ident: 10.1016/j.neunet.2024.106230_b76 article-title: Test-time adaptable neural networks for robust medical image segmentation publication-title: Medical Image Analysis doi: 10.1016/j.media.2020.101907 – volume: 81 start-page: 82 issue: 393 year: 1986 ident: 10.1016/j.neunet.2024.106230_b190 article-title: Accurate approximations for posterior moments and marginal densities publication-title: Journal of the American Statistical Association doi: 10.1080/01621459.1986.10478240 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b100 – ident: 10.1016/j.neunet.2024.106230_b16 doi: 10.1109/CVPR52688.2022.00816 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b231 – ident: 10.1016/j.neunet.2024.106230_b243 doi: 10.1145/3503161.3548410 – volume: 26 start-page: 4230 year: 2023 ident: 10.1016/j.neunet.2024.106230_b159 article-title: Parameter-efficient and student-friendly knowledge distillation publication-title: IEEE Transactions on Multimedia doi: 10.1109/TMM.2023.3321480 – ident: 10.1016/j.neunet.2024.106230_b43 doi: 10.1109/ICCV.2013.208 – start-page: 1 year: 2021 ident: 10.1016/j.neunet.2024.106230_b1 article-title: VirtualGAN: Reducing mode collapse in generative adversarial networks using virtual mapping – year: 2022 ident: 10.1016/j.neunet.2024.106230_b103 – volume: 70 start-page: 1373 year: 2021 ident: 10.1016/j.neunet.2024.106230_b145 article-title: Confident learning: Estimating uncertainty in dataset labels publication-title: Journal of Artificial Intelligence Research doi: 10.1613/jair.1.12125 – volume: 3 start-page: 1 issue: 1 year: 2011 ident: 10.1016/j.neunet.2024.106230_b17 article-title: Distributed optimization and statistical learning via the alternating direction method of multipliers publication-title: Foundations and Trends® in Machine Learning doi: 10.1561/2200000016 – year: 2016 ident: 10.1016/j.neunet.2024.106230_b110 – volume: 69 start-page: 1173 issue: 3 year: 2021 ident: 10.1016/j.neunet.2024.106230_b53 article-title: Domain adaptation for medical image analysis: A survey publication-title: IEEE Transactions on Biomedical Engineering doi: 10.1109/TBME.2021.3117407 – ident: 10.1016/j.neunet.2024.106230_b90 doi: 10.1109/ICCV48922.2021.00696 – volume: 33 start-page: 16282 year: 2020 ident: 10.1016/j.neunet.2024.106230_b164 article-title: Universal domain adaptation through self supervision publication-title: Advances in Neural Information Processing Systems – year: 2020 ident: 10.1016/j.neunet.2024.106230_b35 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b86 – volume: 161 start-page: 682 year: 2023 ident: 10.1016/j.neunet.2024.106230_b97 article-title: Feature alignment by uncertainty and self-training for source-free unsupervised domain adaptation publication-title: Neural Networks doi: 10.1016/j.neunet.2023.02.009 – start-page: 1091 year: 2022 ident: 10.1016/j.neunet.2024.106230_b101 article-title: Adaptive pseudo labeling for source-free domain adaptation in medical image segmentation – ident: 10.1016/j.neunet.2024.106230_b82 doi: 10.1109/ICCV48922.2021.00650 – year: 2017 ident: 10.1016/j.neunet.2024.106230_b152 – ident: 10.1016/j.neunet.2024.106230_b129 doi: 10.1109/CVPR46437.2021.00127 – ident: 10.1016/j.neunet.2024.106230_b46 – year: 2021 ident: 10.1016/j.neunet.2024.106230_b206 – volume: 46 start-page: 1664 issue: 3 year: 2021 ident: 10.1016/j.neunet.2024.106230_b33 article-title: Where and how to transfer: Knowledge aggregation-induced transferability perception for unsupervised domain adaptation publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2021.3128560 – volume: 72 year: 2021 ident: 10.1016/j.neunet.2024.106230_b58 article-title: Autoencoder based self-supervised test-time adaptation for medical image analysis publication-title: Medical Image Analysis doi: 10.1016/j.media.2021.102136 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b123 – volume: 56 start-page: 149 issue: 1 year: 2005 ident: 10.1016/j.neunet.2024.106230_b7 article-title: Human category learning publication-title: Annual Review of Psychology doi: 10.1146/annurev.psych.56.091103.070217 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b219 – ident: 10.1016/j.neunet.2024.106230_b209 doi: 10.1109/ICCV48922.2021.00888 – ident: 10.1016/j.neunet.2024.106230_b240 doi: 10.1109/CVPR42600.2020.00874 – start-page: 1 year: 2022 ident: 10.1016/j.neunet.2024.106230_b39 article-title: Generating privacy preserving synthetic medical data – year: 2020 ident: 10.1016/j.neunet.2024.106230_b63 – year: 2022 ident: 10.1016/j.neunet.2024.106230_b42 article-title: Unsupervised cross-domain functional MRI adaptation for automated major depressive disorder identification publication-title: Medical Image Analysis – start-page: 448 year: 2015 ident: 10.1016/j.neunet.2024.106230_b69 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift – year: 2019 ident: 10.1016/j.neunet.2024.106230_b151 – year: 2023 ident: 10.1016/j.neunet.2024.106230_b244 – ident: 10.1016/j.neunet.2024.106230_b115 doi: 10.1109/CVPR.2019.00309 – ident: 10.1016/j.neunet.2024.106230_b95 doi: 10.1109/CVPR.2019.01053 – volume: 54 start-page: 1 issue: 4 year: 2021 ident: 10.1016/j.neunet.2024.106230_b161 article-title: A comprehensive survey of neural architecture search: Challenges and solutions publication-title: ACM Computing Surveys doi: 10.1145/3447582 – start-page: 248 year: 2009 ident: 10.1016/j.neunet.2024.106230_b30 article-title: ImageNet: A large-scale hierarchical image database – ident: 10.1016/j.neunet.2024.106230_b213 doi: 10.1109/CVPR.2018.00417 – ident: 10.1016/j.neunet.2024.106230_b235 – start-page: 111 year: 2022 ident: 10.1016/j.neunet.2024.106230_b3 article-title: Cross-modal knowledge transfer without task-relevant source data – year: 2021 ident: 10.1016/j.neunet.2024.106230_b36 – volume: 32 start-page: 4309 issue: 10 year: 2020 ident: 10.1016/j.neunet.2024.106230_b41 article-title: Open set domain adaptation: Theoretical bound and algorithm publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2020.3017213 – volume: 34 start-page: 9587 issue: 12 year: 2023 ident: 10.1016/j.neunet.2024.106230_b180 article-title: Towards personalized federated learning publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2022.3160699 – start-page: 30976 year: 2023 ident: 10.1016/j.neunet.2024.106230_b169 article-title: On balancing bias and variance in unsupervised multi-source-free domain adaptation – ident: 10.1016/j.neunet.2024.106230_b2 doi: 10.1109/WACV51458.2022.00286 – volume: 2018 year: 2018 ident: 10.1016/j.neunet.2024.106230_b193 article-title: Deep learning for computer vision: A brief review publication-title: Computational Intelligence and Neuroscience doi: 10.1155/2018/7068349 – start-page: 2681 year: 2023 ident: 10.1016/j.neunet.2024.106230_b210 article-title: Adversarially robust source-free domain adaptation with relaxed adversarial training – volume: 32 start-page: 604 issue: 2 year: 2020 ident: 10.1016/j.neunet.2024.106230_b146 article-title: A survey of the usages of deep learning for natural language processing publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2020.2979670 – volume: 191 year: 2023 ident: 10.1016/j.neunet.2024.106230_b249 article-title: Universal source-free domain adaptation method for cross-domain fault diagnosis of machines publication-title: Mechanical Systems and Signal Processing doi: 10.1016/j.ymssp.2023.110159 – volume: 32 year: 2019 ident: 10.1016/j.neunet.2024.106230_b12 article-title: MixMatch: A holistic approach to semi-supervised learning publication-title: Advances in Neural Information Processing Systems – start-page: 1180 year: 2015 ident: 10.1016/j.neunet.2024.106230_b49 article-title: Unsupervised domain adaptation by backpropagation – start-page: 1 year: 2020 ident: 10.1016/j.neunet.2024.106230_b250 article-title: Discriminative joint probability maximum mean discrepancy (DJP-MMD) for domain adaptation – volume: 20 start-page: 1997 issue: 1 year: 2019 ident: 10.1016/j.neunet.2024.106230_b38 article-title: Neural architecture search: A survey publication-title: Journal of Machine Learning Research – volume: 31 start-page: 3359 year: 2022 ident: 10.1016/j.neunet.2024.106230_b173 article-title: Spot-adaptive knowledge distillation publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2022.3170728 – ident: 10.1016/j.neunet.2024.106230_b168 doi: 10.1109/CVPR.2018.00395 – ident: 10.1016/j.neunet.2024.106230_b92 – ident: 10.1016/j.neunet.2024.106230_b112 doi: 10.1109/ICCV.2017.591 – volume: 45 start-page: 4396 issue: 4 year: 2022 ident: 10.1016/j.neunet.2024.106230_b257 article-title: Domain generalization: A survey publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 41 start-page: 1897 issue: 7 year: 2022 ident: 10.1016/j.neunet.2024.106230_b127 article-title: A source-free domain adaptive polyp detection framework with style diversification flow publication-title: IEEE Transactions on Medical Imaging doi: 10.1109/TMI.2022.3150435 |
| SSID | ssj0006843 |
| Score | 2.6611567 |
| SecondaryResourceType | review_article |
| Snippet | Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy... |
| SourceID | pubmedcentral proquest pubmed crossref elsevier |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 106230 |
| SubjectTerms | Deep Learning Domain adaptation Humans Neural Networks, Computer Source-free Survey Unsupervised learning Unsupervised Machine Learning |
| Title | Source-free unsupervised domain adaptation: A survey |
| URI | https://dx.doi.org/10.1016/j.neunet.2024.106230 https://www.ncbi.nlm.nih.gov/pubmed/38490115 https://www.proquest.com/docview/2958299422 https://pubmed.ncbi.nlm.nih.gov/PMC11015964 |
| Volume | 174 |
| WOSCitedRecordID | wos001216450500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-2782 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006843 issn: 0893-6080 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELdYh9BexjeUjylIvFWuMtuJbd6qaQjQmCZRROElchNnzbS5oWm2_flc4jhNV6EBEi9R5dqtfb9fzmf7fIfQW83AhtbSx5pohllAOZapSLAitNJ-IpS6RvqIHx-LyUSeNO62RZ1OgBsjrq9l_l-hhjIAu7o6-xdwtz8KBfAZQIcnwA7PPwL-S70dj9OF1oPSFGVeaYMC7MpkfqEyM1CJypetT8doUJSLy_XD3SpgByBnrIf46oJIs7X8vfyZtcpC5dbL9wqPZx2mHdnQBN90dt7W_TEr64lubk6XZXe3gbCVV5RTSpLi0LfZl4baKk3BJSZcrGtVzjp6ERaepDl_0TcKNnS43U44GxpdwkCHVS-Gm9VBRPlFDSEVrLo_G6xmtNbP8OTzAZg3YLGFbAttEx5I0UPbo4-Hk0_tdB0K61rpBubuV9ZOgJt92EH33B_-zpTZXKrc9LjtmDDjB2i3WXt4I8uZh-iONo_QfZfXw2vU_GPEOhTyuhTyLIW8FYXeeSPPEugJ-vr-cHzwATfZNXDMQrbEMU2lIGrKqVZTFTDGUyqF2lecMUlUGIcClrZiGvB9zWIC77IvaapSmsIkqsOEPkU9Mzf6OfJSxRQJppoKIlmikmlCfEVFkOpA-2ni9xF1goriJvR8lQHlPHI-hmeRlXRUSTqyku4j3LbKbeiVW-pzh0HUmI_WLIyAWbe0fOMgi0C7Vkdmyuh5WUREBjAmyQjpo2cWwrYvjgZ9JNbAbStUkdvXvzHZrI7g7kj54t-bvkQ7q_fzFeotF6V-je7Gl8usWOyhLT4Rew3VfwFEb71T |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Source-free+unsupervised+domain+adaptation%3A+A+survey&rft.jtitle=Neural+networks&rft.au=Fang%2C+Yuqi&rft.au=Yap%2C+Pew-Thian&rft.au=Lin%2C+Weili&rft.au=Zhu%2C+Hongtu&rft.date=2024-06-01&rft.issn=0893-6080&rft.eissn=1879-2782&rft.volume=174&rft.spage=106230&rft.epage=106230&rft_id=info:doi/10.1016%2Fj.neunet.2024.106230&rft_id=info%3Apmid%2F38490115&rft.externalDocID=PMC11015964 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon |