Maximum Density Divergence for Domain Adaptation

Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 43; číslo 11; s. 3918 - 3930
Hlavní autoři:	Li, Jingjing, Chen, Erpeng, Ding, Zhengming, Zhu, Lei, Lu, Ke, Shen, Heng Tao
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.11.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Adaptation Adaptation models adversarial learning Benchmark testing Density Domain adaptation Domains Empirical analysis Games Kernel Learning Measurement Performance evaluation Task analysis Training transfer learning
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named adversarial tight match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named maximum density divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence ("match" in ATM) and maximizes the intra-class density ("tight" in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on four benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations.
AbstractList	Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named adversarial tight match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named maximum density divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence (“match” in ATM) and maximizes the intra-class density (“tight” in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on four benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations. Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named Adversarial Tight Match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named Maximum Density Divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence ("match" in ATM) and maximizes the intra-class density ("tight" in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on five benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations. Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named adversarial tight match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named maximum density divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence ("match" in ATM) and maximizes the intra-class density ("tight" in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on four benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations.Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two domains have distinctive data distributions. Thus, the essence of domain adaptation is to mitigate the distribution divergence between the two domains. The state-of-the-art methods practice this very idea by either conducting adversarial training or minimizing a metric which defines the distribution gaps. In this paper, we propose a new domain adaptation method named adversarial tight match (ATM) which enjoys the benefits of both adversarial training and metric learning. Specifically, at first, we propose a novel distance loss, named maximum density divergence (MDD), to quantify the distribution divergence. MDD minimizes the inter-domain divergence ("match" in ATM) and maximizes the intra-class density ("tight" in ATM). Then, to address the equilibrium challenge issue in adversarial domain adaptation, we consider leveraging the proposed MDD into adversarial domain adaptation framework. At last, we tailor the proposed MDD as a practical learning loss and report our ATM. Both empirical evaluation and theoretical analysis are reported to verify the effectiveness of the proposed method. The experimental results on four benchmarks, both classical and large-scale, show that our method is able to achieve new state-of-the-art performance on most evaluations.
Author	Chen, Erpeng Zhu, Lei Lu, Ke Ding, Zhengming Li, Jingjing Shen, Heng Tao
Author_xml	– sequence: 1 givenname: Jingjing orcidid: 0000-0002-5504-2529 surname: Li fullname: Li, Jingjing email: lijin117@yeah.net organization: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 2 givenname: Erpeng surname: Chen fullname: Chen, Erpeng email: cep1126@163.com organization: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 3 givenname: Zhengming surname: Ding fullname: Ding, Zhengming email: zd2@iu.edu organization: Department of Computer, Information and Technology, Indiana University-Purdue University Indianapolis, Indianapolis, IN, USA – sequence: 4 givenname: Lei orcidid: 0000-0002-2993-7142 surname: Zhu fullname: Zhu, Lei email: leizhu0608@gmail.com organization: Shandong Normal University, Jinan, China – sequence: 5 givenname: Ke orcidid: 0000-0002-3456-4993 surname: Lu fullname: Lu, Ke email: kel@uestc.edu.cn organization: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 6 givenname: Heng Tao orcidid: 0000-0002-2999-2088 surname: Shen fullname: Shen, Heng Tao email: shenhengtao@hotmail.com organization: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/32356736$$D View this record in MEDLINE/PubMed
BookMark	eNp9kD1PwzAQhi0EglL4AyChSCwsKedz7Nhj1fIlgWCA2TLJBRk1SbETBP-elBYGBpa75Xle3b37bLtpG2LsiMOEczDnjw_Tu5sJAsIEjeEgYYuNkCtIDRrcZiPgClOtUe-x_RhfAXgmQeyyPYFCqlyoEYM79-Hrvk7m1ETffSZz_07hhZqCkqoNybytnW-SaemWnet82xywncotIh1u9pg9XV48zq7T2_urm9n0Ni2E5F2KGiCrwBSOXMazUoEwmpsKMq0V11BJetY5SMolOENSIQ2jyLXmgFSWYszO1rnL0L71FDtb-1jQYuEaavtoUZhc5auwAT39g762fWiG6yzKXKNQODw8Zicbqn-uqbTL4GsXPu1PFwOg10AR2hgDVbbw65-74PzCcrCr2u137XZVu93UPqj4R_1J_1c6XkueiH4FAxo4l-IL9lGKCg
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1016_j_patcog_2024_110653 crossref_primary_10_32604_cmc_2024_049484 crossref_primary_10_1109_TPAMI_2025_3541207 crossref_primary_10_1109_JAS_2023_123342 crossref_primary_10_1016_j_patcog_2023_109787 crossref_primary_10_1109_TMM_2023_3251094 crossref_primary_10_1007_s10845_023_02232_y crossref_primary_10_1109_TMM_2023_3272742 crossref_primary_10_1007_s00530_024_01444_3 crossref_primary_10_1016_j_neunet_2020_06_016 crossref_primary_10_1109_JIOT_2024_3466924 crossref_primary_10_1109_TIP_2023_3261758 crossref_primary_10_1109_TKDE_2021_3060473 crossref_primary_10_1016_j_eswa_2022_117978 crossref_primary_10_1109_TCSVT_2022_3230963 crossref_primary_10_1109_TPAMI_2021_3071225 crossref_primary_10_1117_1_JEI_33_5_053015 crossref_primary_10_1016_j_media_2024_103103 crossref_primary_10_1109_TGRS_2025_3531424 crossref_primary_10_1016_j_ins_2023_119240 crossref_primary_10_1049_2024_1561351 crossref_primary_10_1007_s10115_023_02043_w crossref_primary_10_1109_TIP_2022_3216781 crossref_primary_10_1109_TNNLS_2022_3199619 crossref_primary_10_1016_j_neucom_2023_126624 crossref_primary_10_1109_TCSVT_2023_3242614 crossref_primary_10_1109_TCSVT_2022_3232112 crossref_primary_10_1109_TTE_2021_3109636 crossref_primary_10_1007_s10462_024_10858_4 crossref_primary_10_1088_1742_6596_2278_1_012032 crossref_primary_10_1007_s13042_024_02165_9 crossref_primary_10_1109_TCYB_2021_3104612 crossref_primary_10_1109_TMI_2022_3193146 crossref_primary_10_1109_TNSE_2023_3304986 crossref_primary_10_1016_j_patcog_2022_108987 crossref_primary_10_1145_3565368 crossref_primary_10_1109_TIP_2022_3140614 crossref_primary_10_1016_j_imavis_2023_104755 crossref_primary_10_1088_1741_2552_ad09ff crossref_primary_10_1109_TGRS_2024_3480091 crossref_primary_10_1109_TCSVT_2024_3440517 crossref_primary_10_1109_TMM_2023_3245420 crossref_primary_10_1109_TPEL_2022_3220760 crossref_primary_10_1109_TPAMI_2021_3128560 crossref_primary_10_1007_s11432_022_3851_1 crossref_primary_10_1109_TMI_2025_3525902 crossref_primary_10_1109_TPAMI_2023_3238727 crossref_primary_10_1007_s13042_022_01608_5 crossref_primary_10_1109_ACCESS_2021_3052511 crossref_primary_10_1109_TCYB_2022_3163432 crossref_primary_10_1109_TPAMI_2025_3557502 crossref_primary_10_1109_LSP_2020_3025061 crossref_primary_10_1109_ACCESS_2021_3087867 crossref_primary_10_1016_j_eswa_2025_126744 crossref_primary_10_1016_j_bspc_2024_107483 crossref_primary_10_1109_TCCN_2024_3485083 crossref_primary_10_1016_j_patcog_2024_110473 crossref_primary_10_1016_j_neucom_2025_131498 crossref_primary_10_1109_TMM_2021_3134168 crossref_primary_10_1007_s00530_024_01314_y crossref_primary_10_1109_TIM_2022_3200667 crossref_primary_10_1109_TCYB_2021_3071451 crossref_primary_10_1109_TPAMI_2024_3507534 crossref_primary_10_1145_3632524 crossref_primary_10_1016_j_compbiomed_2024_107998 crossref_primary_10_1109_TMM_2022_3145237 crossref_primary_10_1016_j_inffus_2023_101912 crossref_primary_10_1145_3729483 crossref_primary_10_1109_TNNLS_2021_3070085 crossref_primary_10_3390_rs16111983 crossref_primary_10_1109_TIP_2024_3353539 crossref_primary_10_1109_TNNLS_2021_3134673 crossref_primary_10_1109_TIM_2025_3580817 crossref_primary_10_1109_TMM_2022_3148592 crossref_primary_10_1109_TIM_2025_3557120 crossref_primary_10_1109_TIM_2023_3309381 crossref_primary_10_1007_s10489_022_03306_9 crossref_primary_10_1016_j_compind_2021_103572 crossref_primary_10_1016_j_knosys_2022_110205 crossref_primary_10_1109_JIOT_2025_3573713 crossref_primary_10_1016_j_patcog_2024_110409 crossref_primary_10_1109_ACCESS_2020_3007147 crossref_primary_10_1016_j_apenergy_2025_126691 crossref_primary_10_1109_TIP_2022_3152052 crossref_primary_10_1109_TNNLS_2021_3073119 crossref_primary_10_1007_s41060_021_00274_0 crossref_primary_10_1016_j_neunet_2020_11_015 crossref_primary_10_1109_TAI_2022_3196813 crossref_primary_10_1109_TMM_2023_3312917 crossref_primary_10_1007_s10462_022_10230_4 crossref_primary_10_1109_TNNLS_2021_3105868 crossref_primary_10_1016_j_imavis_2023_104695 crossref_primary_10_1109_TCYB_2021_3052536 crossref_primary_10_1109_TPAMI_2024_3438154 crossref_primary_10_3390_e24010044 crossref_primary_10_1007_s10994_025_06751_y crossref_primary_10_1007_s11517_025_03287_0 crossref_primary_10_1016_j_ipm_2024_103730 crossref_primary_10_1109_ACCESS_2020_3015334 crossref_primary_10_1109_TGRS_2024_3412401 crossref_primary_10_1109_TMM_2021_3063616 crossref_primary_10_1109_TPAMI_2021_3109287 crossref_primary_10_1109_TPAMI_2024_3370978 crossref_primary_10_1016_j_eswa_2024_124509 crossref_primary_10_1007_s11263_025_02497_1 crossref_primary_10_1016_j_knosys_2025_113850 crossref_primary_10_1007_s00521_023_08269_7 crossref_primary_10_1109_TIM_2025_3527531 crossref_primary_10_1109_TNNLS_2021_3071474 crossref_primary_10_1016_j_engappai_2024_109324 crossref_primary_10_1109_TNNLS_2022_3177769 crossref_primary_10_1109_TSMC_2022_3195239 crossref_primary_10_1016_j_ipm_2020_102367 crossref_primary_10_1109_TIM_2022_3217563 crossref_primary_10_1109_TNNLS_2021_3072041 crossref_primary_10_1109_TKDE_2025_3592614 crossref_primary_10_1109_TGRS_2025_3559915 crossref_primary_10_1109_TIP_2025_3533199 crossref_primary_10_1016_j_inffus_2023_102020 crossref_primary_10_1016_j_media_2022_102607 crossref_primary_10_3390_s25092818 crossref_primary_10_1109_TFUZZ_2024_3367460 crossref_primary_10_1016_j_measurement_2023_112937 crossref_primary_10_1109_TTE_2023_3293551 crossref_primary_10_1007_s11042_023_15683_5 crossref_primary_10_1109_TMM_2022_3233398 crossref_primary_10_1109_TMM_2022_3233306 crossref_primary_10_1007_s10994_023_06432_8 crossref_primary_10_1109_ACCESS_2021_3098713 crossref_primary_10_1109_TITS_2023_3314680 crossref_primary_10_1007_s11263_024_02174_9 crossref_primary_10_1016_j_neunet_2024_106626 crossref_primary_10_1109_TPAMI_2024_3412680 crossref_primary_10_1109_TCYB_2021_3110128 crossref_primary_10_1109_TNSE_2022_3201529 crossref_primary_10_1016_j_engappai_2025_112330 crossref_primary_10_1109_TNNLS_2022_3193289 crossref_primary_10_1016_j_ins_2022_01_044 crossref_primary_10_1109_TGRS_2023_3320805 crossref_primary_10_1109_TCSVT_2023_3249200 crossref_primary_10_1109_TCYB_2021_3054978 crossref_primary_10_1109_TPAMI_2025_3572963 crossref_primary_10_1016_j_patcog_2024_111270 crossref_primary_10_1109_ACCESS_2023_3305924 crossref_primary_10_1016_j_neunet_2023_08_005 crossref_primary_10_1109_TSMC_2023_3324735 crossref_primary_10_3390_math10183223 crossref_primary_10_1109_TIP_2023_3318955 crossref_primary_10_1016_j_ins_2022_07_083 crossref_primary_10_1109_ACCESS_2021_3123281 crossref_primary_10_1109_TGRS_2024_3367922 crossref_primary_10_1109_ACCESS_2020_3027850 crossref_primary_10_1109_TMM_2021_3087098 crossref_primary_10_1109_TIP_2025_3541868 crossref_primary_10_1109_TIFS_2025_3569409 crossref_primary_10_1109_ACCESS_2021_3076533 crossref_primary_10_1016_j_compbiomed_2023_106570 crossref_primary_10_1016_j_patcog_2025_112095 crossref_primary_10_1016_j_ins_2024_121359 crossref_primary_10_1016_j_patrec_2022_06_015 crossref_primary_10_1109_TIFS_2025_3576576 crossref_primary_10_1109_TPEL_2023_3251568 crossref_primary_10_1109_TIM_2025_3542138 crossref_primary_10_1109_TII_2020_3032690 crossref_primary_10_1109_TCYB_2021_3133890 crossref_primary_10_1016_j_aei_2024_102948 crossref_primary_10_1109_ACCESS_2023_3337438 crossref_primary_10_1016_j_patcog_2022_108960 crossref_primary_10_1109_TMM_2024_3407697 crossref_primary_10_1109_ACCESS_2022_3218337 crossref_primary_10_1109_TMM_2022_3141886 crossref_primary_10_1016_j_knosys_2025_114316 crossref_primary_10_1088_1741_2552_ad9957 crossref_primary_10_1109_TIP_2025_3526380 crossref_primary_10_1016_j_knosys_2023_110397 crossref_primary_10_1109_JIOT_2024_3490037 crossref_primary_10_3390_app15052625 crossref_primary_10_1109_TPAMI_2024_3444904 crossref_primary_10_1109_TPAMI_2022_3190645
Cites_doi	10.24963/ijcai.2018/767 10.1109/TNNLS.2018.2868854 10.1109/CVPR.2016.90 10.1109/CVPR.2017.572 10.1109/CVPR.2018.00845 10.1109/TNN.2010.2091281 10.1109/TIP.2018.2851067 10.1145/3343031.3350902 10.1007/s11263-015-0816-y 10.1007/978-3-319-46493-0_36 10.1109/CVPR.2017.316 10.1007/978-3-319-49409-8_35 10.1007/978-3-642-15561-1_16 10.1090/mbk/107 10.1109/TCYB.2020.2974106 10.1007/s11263-014-0696-6 10.1109/TCYB.2018.2820174 10.1109/TPAMI.2019.2945942 10.1007/s10994-009-5152-4 10.1109/CVPR.2018.00887 10.1109/TKDE.2009.191 10.1109/TIP.2019.2924174 10.1109/TPAMI.2020.2964173
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TPAMI.2020.2991050
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	Technology Research Database PubMed 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: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2160-9292 1939-3539
EndPage	3930
ExternalDocumentID	32356736 10_1109_TPAMI_2020_2991050 9080115
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 61806039; 61832001 funderid: 10.13039/501100001809 – fundername: National Key Research and Development Program of China grantid: 2018YFE0203900 funderid: 10.13039/501100012166 – fundername: Sichuan Department of Science and Technology grantid: 20ZDYF2771
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 AAYXX CITATION NPM RIC Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c351t-28004f09caea414d6039819f04886180f5eb8705e750a9e562ee56c788102edd3
IEDL.DBID	RIE
ISICitedReferencesCount	204
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000702649700017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Mon Sep 29 05:46:50 EDT 2025 Sun Nov 09 06:08:59 EST 2025 Wed Feb 19 02:30:42 EST 2025 Sat Nov 29 05:15:59 EST 2025 Tue Nov 18 22:13:16 EST 2025 Wed Aug 27 02:26:59 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	11
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c351t-28004f09caea414d6039819f04886180f5eb8705e750a9e562ee56c788102edd3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-3456-4993 0000-0002-5504-2529 0000-0002-2999-2088 0000-0002-2993-7142
PMID	32356736
PQID	2578236232
PQPubID	85458
PageCount	13
ParticipantIDs	proquest_miscellaneous_2397678861 ieee_primary_9080115 proquest_journals_2578236232 pubmed_primary_32356736 crossref_citationtrail_10_1109_TPAMI_2020_2991050 crossref_primary_10_1109_TPAMI_2020_2991050
PublicationCentury	2000
PublicationDate	2021-11-01
PublicationDateYYYYMMDD	2021-11-01
PublicationDate_xml	– month: 11 year: 2021 text: 2021-11-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationTitleAlternate	IEEE Trans Pattern Anal Mach Intell
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref35 ref12 ref37 ref15 ref36 gretton (ref17) 2012; 13 ref33 ref11 ref10 netzer (ref34) 2011 ref2 ref1 ref38 ref18 van der maaten (ref44) 2008; 9 goodfellow (ref13) 2014 liu (ref19) 2016 ganin (ref20) 2016; 17 tzeng (ref41) 2014 ref23 ref26 long (ref4) 2018 hoffman (ref3) 2018 ref42 ref22 ref21 xie (ref32) 2018 krizhevsky (ref43) 2012 arora (ref14) 2017 ref28 zhao (ref31) 2019 long (ref16) 2017 ref8 ref7 mirza (ref29) 2014 shu (ref30) 2018 ref9 french (ref39) 2018 ref6 székely (ref27) 2003; 3 ref40 zhuang (ref25) 2015 ganin (ref5) 2015 long (ref24) 2015
References_xml	– volume: 3 start-page: 1 year: 2003 ident: ref27 article-title: E-statistics: The energy of statistical samples publication-title: Bowling Green State Univ Dept Math Statist Tech Rep – start-page: 1994 year: 2018 ident: ref3 article-title: CyCADA: Cycle-consistent adversarial domain adaptation publication-title: Proc Int Conf Mach Learn – ident: ref12 doi: 10.24963/ijcai.2018/767 – ident: ref21 doi: 10.1109/TNNLS.2018.2868854 – ident: ref36 doi: 10.1109/CVPR.2016.90 – ident: ref11 doi: 10.1109/CVPR.2017.572 – ident: ref37 doi: 10.1109/CVPR.2018.00845 – ident: ref40 doi: 10.1109/TNN.2010.2091281 – year: 2018 ident: ref39 article-title: Self-ensembling for visual domain adaptation publication-title: Proc Int Conf Learn Representations – year: 2014 ident: ref29 article-title: Conditional generative adversarial nets – ident: ref22 doi: 10.1109/TIP.2018.2851067 – year: 2014 ident: ref41 article-title: Deep domain confusion: Maximizing for domain invariance – start-page: 2672 year: 2014 ident: ref13 article-title: Generative adversarial nets publication-title: Proc 27th Int Conf Neural Inf Process Syst – start-page: 224 year: 2017 ident: ref14 article-title: Generalization and equilibrium in generative adversarial nets (GANs) publication-title: Proc Int Conf Mach Learn – ident: ref28 doi: 10.1145/3343031.3350902 – year: 2011 ident: ref34 article-title: Reading digits in natural images with unsupervised feature learning publication-title: Proc NeurIPS Workshop Deep Learn Unsupervised Feature Learn – start-page: 1180 year: 2015 ident: ref5 article-title: Unsupervised domain adaptation by backpropagation – ident: ref1 doi: 10.1007/s11263-015-0816-y – volume: 17 start-page: 2096 year: 2016 ident: ref20 article-title: Domain-adversarial training of neural networks publication-title: J Mach Learn Res – volume: 13 start-page: 723 year: 2012 ident: ref17 article-title: A kernel two-sample test publication-title: J Mach Learn Res – ident: ref38 doi: 10.1007/978-3-319-46493-0_36 – ident: ref7 doi: 10.1109/CVPR.2017.316 – ident: ref15 doi: 10.1007/978-3-319-49409-8_35 – start-page: 469 year: 2016 ident: ref19 article-title: Coupled generative adversarial networks publication-title: Proc Int Conf Neural Inf Process – start-page: 4119 year: 2015 ident: ref25 article-title: Supervised representation learning: Transfer learning with deep autoencoders publication-title: Proc Int Joint Conf Artif Intell – ident: ref35 doi: 10.1007/978-3-642-15561-1_16 – ident: ref33 doi: 10.1090/mbk/107 – start-page: 1647 year: 2018 ident: ref4 article-title: Conditional adversarial domain adaptation publication-title: Proc 32nd Int Conf Neural Inf Process Syst – ident: ref23 doi: 10.1109/TCYB.2020.2974106 – start-page: 2208 year: 2017 ident: ref16 article-title: Deep transfer learning with joint adaptation networks publication-title: Proc Int Conf Mach Learn – start-page: 5419 year: 2018 ident: ref32 article-title: Learning semantic representations for unsupervised domain adaptation publication-title: Proc Int Conf Mach Learn – volume: 9 start-page: 2579 year: 2008 ident: ref44 article-title: Visualizing data using t-SNE publication-title: J Mach Learn Res – ident: ref6 doi: 10.1007/s11263-014-0696-6 – ident: ref10 doi: 10.1109/TCYB.2018.2820174 – start-page: 97 year: 2015 ident: ref24 article-title: Learning transferable features with deep adaptation networks publication-title: Proc Int Conf Mach Learn – ident: ref9 doi: 10.1109/TPAMI.2019.2945942 – ident: ref18 doi: 10.1007/s10994-009-5152-4 – ident: ref42 doi: 10.1109/CVPR.2018.00887 – ident: ref2 doi: 10.1109/TKDE.2009.191 – year: 2018 ident: ref30 article-title: A DIRT-T approach to unsupervised domain adaptation – ident: ref26 doi: 10.1109/TIP.2019.2924174 – ident: ref8 doi: 10.1109/TPAMI.2020.2964173 – start-page: 7523 year: 2019 ident: ref31 article-title: On learning invariant representations for domain adaptation publication-title: Proc Int Conf Mach Learn – start-page: 1097 year: 2012 ident: ref43 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Int Conf Neural Inf Process
SSID	ssj0014503
Score	2.7309418
Snippet	Unsupervised domain adaptation addresses the problem of transferring knowledge from a well-labeled source domain to an unlabeled target domain where the two...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	3918
SubjectTerms	Adaptation Adaptation models adversarial learning Benchmark testing Density Domain adaptation Domains Empirical analysis Games Kernel Learning Measurement Performance evaluation Task analysis Training transfer learning
Title	Maximum Density Divergence for Domain Adaptation
URI	https://ieeexplore.ieee.org/document/9080115 https://www.ncbi.nlm.nih.gov/pubmed/32356736 https://www.proquest.com/docview/2578236232 https://www.proquest.com/docview/2397678861
Volume	43
WOSCitedRecordID	wos000702649700017&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: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5q8aAH34_4IoI3jW6yG5Mci1X0UPGg0FvYbCZQsKnYVvTfO7N5oKCClxDI5sE8dr7JvABOwpggm5GFp_xCeEpr5WVSGU9hLFVIJgVzY4dNRPf38XCYPHTgrK2FQUSbfIbnfGpj-fnEzPlX2UVC8MbnivKFKIqqWq02YqBCOwWZEAxpOLkRTYGMSC4eH3qDO3IFA3FOmy8BCh7_JgMZck7TN3tkB6z8jjWtzblZ_d_XrsFKjS3dXiUM69DBcgNWm7kNbq3GG7D8pQnhJoiBfh-N52O3z7nssw-3z6katkenS4jW7U_GelS6vVy_VGH7LXi6uX68uvXqOQqekaE_8wIChaoQidGola_ySyETAgIFK--lH4sixIzUNkRCDzpBQkRIB8ON5kWAeS63oVtOStzlRCihTJRxl75IoYm1jrLQ15kmJKESkzvgN9RMTd1knGddPKfW2RBJapmRMjPSmhkOnLb3vFQtNv5cvcmkblfWVHbgoGFaWmvhNOXtKCALLQMHjtvLpD8cFNElTua0hgFZxIRwYKdidvvsRkb2fn7nPiwFnOFiKxMPoDt7neMhLJq32Wj6ekRCOoyPrJB-AiVF3Mc
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1ZS-RAEC5EhdUH7yMeaxb2TaOddLdJHocdRVln8GEWfAudTgUGnIzojOi_t6pz4MLuwr6EQDoHVV1dX6eOD-C7TgiyWVkGKixFoIxRQS6VDRQmUmlyKVhYRzYRD4fJw0N6vwBnXS0MIrrkMzznUxfLL6Z2zr_KLlKCNyFXlC9ppaKwrtbqYgZKOx5kwjBk47SRaEtkRHoxuu8NbmkzGIlzWn4JUjABnIyk5qym3zySo1j5O9p0Xud6_f--dwPWGnTp9-rpsAkLWG3Besvc4DeGvAWrn9oQboMYmLfxZD7x-5zNPnv3-5ys4bp0-oRp_f50YsaV3yvMUx2434Ff11ejHzdBw6QQWKnDWRARLFSlSK1Bo0JVXAqZEhQo2Xwvw0SUGnMyXI2EH0yKhImQDpZbzYsIi0LuwmI1rXCfU6GEsnHOffpihTYxJs51aHJDWEKltvAgbKWZ2abNOLNdPGZuuyHSzCkjY2VkjTI8OO3ueaqbbPxz9DaLuhvZSNmDo1ZpWWOHLxkvSBH5aBl58K27TBbEYRFT4XROYxiSxSwID_ZqZXfPbufIwZ_feQJfbkaDu-zudvjzEFYizndxdYpHsDh7nuMxLNvX2fjl-aubqh-Y6d8m
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=Maximum+Density+Divergence+for+Domain+Adaptation&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Li%2C+Jingjing&rft.au=Chen%2C+Erpeng&rft.au=Ding%2C+Zhengming&rft.au=Zhu%2C+Lei&rft.date=2021-11-01&rft.pub=IEEE&rft.issn=0162-8828&rft.volume=43&rft.issue=11&rft.spage=3918&rft.epage=3930&rft_id=info:doi/10.1109%2FTPAMI.2020.2991050&rft_id=info%3Apmid%2F32356736&rft.externalDocID=9080115
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon