Trusted Multi-View Classification With Dynamic Evidential Fusion
Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations for follow-up tasks. Although effective, it is also crucial to ensure the reliability of both the multi-view integration and the final decis...
Saved in:
| Published in: | IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 2; pp. 2551 - 2566 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
IEEE
01.02.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 0162-8828, 1939-3539, 2160-9292, 1939-3539 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations for follow-up tasks. Although effective, it is also crucial to ensure the reliability of both the multi-view integration and the final decision, especially for noisy, corrupted and out-of-distribution data. Dynamically assessing the trustworthiness of each view for different samples could provide reliable integration. This can be achieved through uncertainty estimation. With this in mind, we propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC), providing a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed TMC can promote classification reliability by considering evidence from each view. Specifically, we introduce the variational Dirichlet to characterize the distribution of the class probabilities, parameterized with evidence from different views and integrated with the Dempster-Shafer theory. The unified learning framework induces accurate uncertainty and accordingly endows the model with both reliability and robustness against possible noise or corruption. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness. |
|---|---|
| AbstractList | Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations for follow-up tasks. Although effective, it is also crucial to ensure the reliability of both the multi-view integration and the final decision, especially for noisy, corrupted and out-of-distribution data. Dynamically assessing the trustworthiness of each view for different samples could provide reliable integration. This can be achieved through uncertainty estimation. With this in mind, we propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC), providing a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed TMC can promote classification reliability by considering evidence from each view. Specifically, we introduce the variational Dirichlet to characterize the distribution of the class probabilities, parameterized with evidence from different views and integrated with the Dempster-Shafer theory. The unified learning framework induces accurate uncertainty and accordingly endows the model with both reliability and robustness against possible noise or corruption. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness.Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations for follow-up tasks. Although effective, it is also crucial to ensure the reliability of both the multi-view integration and the final decision, especially for noisy, corrupted and out-of-distribution data. Dynamically assessing the trustworthiness of each view for different samples could provide reliable integration. This can be achieved through uncertainty estimation. With this in mind, we propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC), providing a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed TMC can promote classification reliability by considering evidence from each view. Specifically, we introduce the variational Dirichlet to characterize the distribution of the class probabilities, parameterized with evidence from different views and integrated with the Dempster-Shafer theory. The unified learning framework induces accurate uncertainty and accordingly endows the model with both reliability and robustness against possible noise or corruption. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness. Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations for follow-up tasks. Although effective, it is also crucial to ensure the reliability of both the multi-view integration and the final decision, especially for noisy, corrupted and out-of-distribution data. Dynamically assessing the trustworthiness of each view for different samples could provide reliable integration. This can be achieved through uncertainty estimation. With this in mind, we propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC), providing a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed TMC can promote classification reliability by considering evidence from each view. Specifically, we introduce the variational Dirichlet to characterize the distribution of the class probabilities, parameterized with evidence from different views and integrated with the Dempster-Shafer theory. The unified learning framework induces accurate uncertainty and accordingly endows the model with both reliability and robustness against possible noise or corruption. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness. |
| Author | Han, Zongbo Zhou, Joey Tianyi Zhang, Changqing Fu, Huazhu |
| Author_xml | – sequence: 1 givenname: Zongbo surname: Han fullname: Han, Zongbo email: zongbo@tju.edu.cn organization: College of Intelligence and Computing, Tianjin University, Tianjin, China – sequence: 2 givenname: Changqing orcidid: 0000-0003-1410-6650 surname: Zhang fullname: Zhang, Changqing email: zhangchangqing@tju.edu.cn organization: College of Intelligence and Computing, Tianjin University, Tianjin, China – sequence: 3 givenname: Huazhu orcidid: 0000-0002-9702-5524 surname: Fu fullname: Fu, Huazhu email: hzfu@ieee.org organization: Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (ASTAR), Singapore – sequence: 4 givenname: Joey Tianyi orcidid: 0000-0002-4675-7055 surname: Zhou fullname: Zhou, Joey Tianyi email: zhouty@ihpc.a-star.edu.sg organization: ASTAR Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (ASTAR), Singapore |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35503823$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kUtPwzAQhC0EouXxB0BCkbhwSVmvY8e5UZXykEBwKHC03GQjjNIEYgfEvyfQwqEHTnPYb3ZXMztss25qYuyAw4hzyE5n9-Pb6xEC4kjwlGdabLAhcgVxhhlusiFwhbHWqAdsx_sXAJ5IENtsIGSvGsWQnc3azgcqotuuCi5-dPQRTSrrvStdboNr6ujJhefo_LO2C5dH03dXUB2craKLzvfjPbZV2srT_kp32cPFdDa5im_uLq8n45s4F5KHWFosbAlpkqVawRwLJcscJAGqwkKiEypAqblMwPKSSJCwogCZpcomoLK52GUny72vbfPWkQ9m4XxOVWVrajpvUMkMBehU9-jxGvrSdG3df2cwVVykCSroqaMV1c0XVJjX1i1s-2l-s-kBXAJ523jfUvmHcDDfBZifAsx3AWZVQG_Sa6bchZ8cQ2td9b_1cGl1RPR3q08gVQrFF3eckNg |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1109_TIP_2025_3587575 crossref_primary_10_1287_ijoc_2023_0448 crossref_primary_10_1016_j_inffus_2024_102754 crossref_primary_10_1109_TGRS_2025_3587876 crossref_primary_10_1109_TIP_2023_3310339 crossref_primary_10_1007_s00138_024_01556_w crossref_primary_10_1016_j_media_2025_103507 crossref_primary_10_1016_j_inffus_2024_102592 crossref_primary_10_1007_s10489_024_06113_6 crossref_primary_10_1109_TMM_2025_3535391 crossref_primary_10_1109_TGRS_2024_3360470 crossref_primary_10_1109_TGRS_2023_3342740 crossref_primary_10_1016_j_eswa_2025_128225 crossref_primary_10_1007_s10489_024_05652_2 crossref_primary_10_1016_j_ins_2024_121577 crossref_primary_10_1109_TAFFC_2023_3340924 crossref_primary_10_3390_math13132136 crossref_primary_10_1109_JAS_2023_123579 crossref_primary_10_1016_j_neucom_2024_129195 crossref_primary_10_1109_TPAMI_2025_3583410 crossref_primary_10_1109_TBDATA_2024_3423694 crossref_primary_10_1016_j_inffus_2024_102400 crossref_primary_10_1007_s13042_025_02606_z crossref_primary_10_1016_j_knosys_2023_111217 crossref_primary_10_1016_j_engappai_2025_112260 crossref_primary_10_3390_ijms25031655 crossref_primary_10_1007_s11554_025_01648_4 crossref_primary_10_1016_j_media_2025_103476 crossref_primary_10_1109_TIP_2024_3504252 crossref_primary_10_1038_s41598_025_93770_3 crossref_primary_10_3390_info16090777 crossref_primary_10_1016_j_media_2024_103294 crossref_primary_10_1109_TIP_2025_3599673 crossref_primary_10_1016_j_ymssp_2024_112058 crossref_primary_10_1109_TFUZZ_2023_3335361 crossref_primary_10_1016_j_ins_2024_121622 crossref_primary_10_1016_j_media_2024_103214 crossref_primary_10_1109_JBHI_2024_3415641 crossref_primary_10_1016_j_eswa_2025_126972 crossref_primary_10_1016_j_neunet_2025_107459 crossref_primary_10_1109_LGRS_2023_3322452 crossref_primary_10_1007_s10044_025_01455_4 crossref_primary_10_1109_JSTARS_2024_3375806 crossref_primary_10_1007_s11227_025_07307_6 crossref_primary_10_1109_JBHI_2023_3346205 crossref_primary_10_1109_TIM_2024_3522632 crossref_primary_10_1109_TNNLS_2023_3329658 crossref_primary_10_1109_TMM_2024_3521733 crossref_primary_10_1109_TMM_2023_3316437 crossref_primary_10_3390_rs16234381 crossref_primary_10_3390_electronics13030662 crossref_primary_10_1109_TPAMI_2025_3546356 crossref_primary_10_1016_j_engappai_2024_108057 crossref_primary_10_1016_j_ins_2024_120342 crossref_primary_10_1109_TIP_2025_3597045 crossref_primary_10_1109_TMM_2024_3379079 crossref_primary_10_1007_s10489_023_04891_z crossref_primary_10_1016_j_knosys_2024_112424 crossref_primary_10_1109_TFUZZ_2024_3470794 crossref_primary_10_1007_s44443_025_00225_w crossref_primary_10_1016_j_eswa_2024_125371 crossref_primary_10_1109_TIP_2024_3420796 crossref_primary_10_1016_j_neunet_2023_10_052 crossref_primary_10_1016_j_sigpro_2025_110216 crossref_primary_10_1016_j_inffus_2024_102605 crossref_primary_10_3390_math10234545 crossref_primary_10_1016_j_eswa_2024_125772 crossref_primary_10_1016_j_eswa_2025_129453 crossref_primary_10_1109_TPAMI_2022_3224978 crossref_primary_10_1109_ACCESS_2024_3399204 crossref_primary_10_1007_s11760_024_03633_z crossref_primary_10_1016_j_compbiomed_2024_108058 crossref_primary_10_1109_TKDE_2025_3527978 crossref_primary_10_1186_s40854_023_00519_w crossref_primary_10_1109_TCSVT_2024_3486344 crossref_primary_10_1016_j_patcog_2025_111639 crossref_primary_10_1109_ACCESS_2025_3599563 crossref_primary_10_1109_TCSVT_2024_3430904 crossref_primary_10_1038_s44172_024_00245_w crossref_primary_10_3390_math10152797 crossref_primary_10_1016_j_media_2025_103697 crossref_primary_10_1007_s00521_023_08651_5 crossref_primary_10_1073_pnas_2309240120 crossref_primary_10_1016_j_neucom_2025_129722 crossref_primary_10_1016_j_engappai_2025_112153 crossref_primary_10_1016_j_engappai_2024_108289 crossref_primary_10_1109_TPAMI_2024_3361978 crossref_primary_10_1016_j_eswa_2025_129742 crossref_primary_10_1109_TKDE_2022_3231929 crossref_primary_10_1016_j_neucom_2025_131117 crossref_primary_10_1016_j_patcog_2025_112284 crossref_primary_10_1016_j_neunet_2024_106763 crossref_primary_10_1007_s13755_023_00247_6 crossref_primary_10_1016_j_eswa_2025_126872 crossref_primary_10_1109_TIP_2025_3579987 crossref_primary_10_1016_j_inffus_2025_103249 crossref_primary_10_1016_j_bspc_2025_108395 crossref_primary_10_1016_j_compbiomed_2024_109312 crossref_primary_10_1016_j_neucom_2025_131475 crossref_primary_10_3390_math11132940 crossref_primary_10_1109_TCSVT_2024_3376564 crossref_primary_10_1109_TCSVT_2024_3375511 crossref_primary_10_1109_TIP_2024_3482175 crossref_primary_10_1111_phor_12534 crossref_primary_10_1016_j_asoc_2024_112538 crossref_primary_10_1109_TITS_2023_3345901 crossref_primary_10_1016_j_jksuci_2023_101904 crossref_primary_10_1016_j_knosys_2024_112247 crossref_primary_10_1016_j_neunet_2025_107783 crossref_primary_10_1109_TNNLS_2024_3482408 crossref_primary_10_1016_j_engappai_2025_111996 crossref_primary_10_1016_j_neunet_2025_107821 crossref_primary_10_1109_JBHI_2025_3539712 crossref_primary_10_26599_BDMA_2024_9020048 crossref_primary_10_1016_j_inffus_2023_102021 crossref_primary_10_1109_TIM_2024_3374311 crossref_primary_10_1016_j_patcog_2025_111651 crossref_primary_10_1109_JSTARS_2024_3354455 crossref_primary_10_1109_TII_2024_3523536 crossref_primary_10_3390_sym17050794 crossref_primary_10_1109_TMM_2024_3406146 crossref_primary_10_1016_j_neucom_2025_130092 crossref_primary_10_1109_TETCI_2024_3423459 crossref_primary_10_1016_j_engappai_2025_111123 crossref_primary_10_1016_j_media_2025_103557 crossref_primary_10_1088_1361_6560_ad2ee4 crossref_primary_10_1016_j_media_2025_103677 crossref_primary_10_1109_JSEN_2024_3370588 crossref_primary_10_1016_j_inffus_2025_102934 crossref_primary_10_1016_j_ins_2024_120178 crossref_primary_10_1016_j_engappai_2025_111887 crossref_primary_10_1016_j_knosys_2025_113164 crossref_primary_10_1016_j_eswa_2024_126198 crossref_primary_10_1109_TIP_2025_3574918 crossref_primary_10_1109_TPAMI_2024_3438349 crossref_primary_10_3389_fonc_2024_1332188 crossref_primary_10_1093_bib_bbad378 crossref_primary_10_1016_j_knosys_2025_113507 crossref_primary_10_1016_j_inffus_2025_103143 crossref_primary_10_1016_j_jag_2025_104356 crossref_primary_10_1016_j_rineng_2025_106413 crossref_primary_10_1109_TIV_2024_3398210 crossref_primary_10_26599_BDMA_2025_9020005 crossref_primary_10_1016_j_knosys_2025_114163 crossref_primary_10_1016_j_neunet_2024_106794 crossref_primary_10_1016_j_imavis_2024_105250 crossref_primary_10_1016_j_knosys_2024_112101 crossref_primary_10_1109_TCE_2024_3357480 crossref_primary_10_1016_j_knosys_2024_111770 crossref_primary_10_1016_j_inffus_2025_103377 crossref_primary_10_1109_TAI_2023_3296092 crossref_primary_10_1016_j_inffus_2024_102661 crossref_primary_10_1109_ACCESS_2025_3559663 crossref_primary_10_1002_ima_23199 crossref_primary_10_1109_TFUZZ_2025_3576112 crossref_primary_10_1109_TPAMI_2025_3547417 crossref_primary_10_1109_TNNLS_2025_3546660 crossref_primary_10_1109_TGRS_2024_3406606 crossref_primary_10_1364_AO_528226 crossref_primary_10_1016_j_inffus_2024_102899 crossref_primary_10_1016_j_neunet_2025_107553 crossref_primary_10_3390_app13063938 crossref_primary_10_1109_TMI_2023_3278259 |
| Cites_doi | 10.1109/CVPR.2012.6247814 10.24963/ijcai.2017/631 10.1145/3474085.3475379 10.1109/TMM.2021.3136094 10.48550/arXiv.1810.04805 10.1007/s00530-010-0182-0 10.1109/CVPR.2016.645 10.1038/nature21056 10.1109/TMM.2013.2267205 10.1162/neco.1992.4.3.448 10.1109/ICCV.2019.00631 10.24963/ijcai.2019/524 10.1038/nature08538 10.1109/TPAMI.2013.2296528 10.1109/CVPR.2005.16 10.1109/ICCV.2019.00640 10.1007/978-3-319-42337-1 10.1016/j.neuron.2019.08.038 10.1109/CVPR.2015.7298655 10.1109/JPROC.2003.817150 10.1109/CVPR.2019.00713 10.1109/CVPR.2019.01211 10.1002/9780470316870 10.18653/v1/D15-1303 10.1109/TFUZZ.2017.2659764 10.1109/36.602544 10.1007/978-0-387-45528-0 10.18653/v1/N16-1020 10.1007/978-3-642-33715-4_54 10.1109/CVPR46437.2021.01102 10.1109/TPAMI.2018.2879108 10.1109/ICMEW.2015.7169757 10.1609/aaai.v32i1.12292 10.18653/v1/P19-1656 10.1145/1027527.1027661 10.1109/ICCV.2011.6126543 10.1111/j.2517-6161.1968.tb00722.x 10.1515/9780691214696 10.1007/978-3-030-58621-8_45 10.2172/800792 10.1038/s41467-018-05432-w 10.1109/CVPR42600.2020.01271 10.1109/TBME.2019.2899222 10.1109/ICIP.2002.1038076 10.1007/978-1-4612-4380-9_14 10.1609/aaai.v32i1.11945 10.1109/ICRA40945.2020.9197266 10.1109/CVPR.2016.90 10.1214/aoms/1177698950 10.1109/ICME.2018.8486573 10.1109/TIP.2018.2872629 10.1109/TNN.2007.891186 10.1109/CVPR.2004.383 10.1609/aaai.v33i01.33019176 10.1109/TNNLS.2021.3117403 10.1109/TIP.2017.2651379 10.5555/3045390.3045502 10.1016/0167-8655(96)00039-6 10.1109/ICCV48922.2021.01310 10.1109/MFI.2010.5604480 10.1038/s41467-021-23774-w 10.1109/CVPR.2017.312 10.5555/2986459.2986721 10.1007/978-3-662-44415-3_16 10.1016/j.inffus.2005.07.003 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TPAMI.2022.3171983 |
| DatabaseName | IEEE Xplore (IEEE) 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 | MEDLINE - Academic PubMed Technology Research Database |
| 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 Electronic Library (IEL) 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 | 2566 |
| ExternalDocumentID | 35503823 10_1109_TPAMI_2022_3171983 9767662 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: AME Programmatic Funding Scheme grantid: A18A1b0045 – fundername: National Key Research and Development Program of China grantid: 2019YFB2101900 – fundername: A*STAR AI3 HTPO Seed Fund grantid: C211118012 – fundername: Joey Tianyi Zhou's A*STAR SERCCentral Research Fund – fundername: National Natural Science Foundation of China grantid: 61976151; 61925602; 61732011 funderid: 10.13039/501100001809 |
| 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 5VS 9M8 AAYOK ABFSI ADRHT AETEA AETIX AGSQL AI. AIBXA ALLEH FA8 H~9 IBMZZ ICLAB IFJZH NPM RIG RNI RZB VH1 XJT 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c351t-5a2daf07497860b2d65fc05e026da0484ed066b540a1fee3e3a3d05976a4069b3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 273 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000912386000078&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 | Sat Sep 27 18:44:45 EDT 2025 Mon Jun 30 06:08:16 EDT 2025 Thu Apr 03 07:03:20 EDT 2025 Sat Nov 29 02:58:19 EST 2025 Tue Nov 18 21:21:28 EST 2025 Wed Aug 27 02:54:13 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| 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-5a2daf07497860b2d65fc05e026da0484ed066b540a1fee3e3a3d05976a4069b3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-9702-5524 0000-0003-1410-6650 0000-0002-4675-7055 |
| PMID | 35503823 |
| PQID | 2761374260 |
| PQPubID | 85458 |
| PageCount | 16 |
| ParticipantIDs | pubmed_primary_35503823 ieee_primary_9767662 proquest_journals_2761374260 proquest_miscellaneous_2659230878 crossref_citationtrail_10_1109_TPAMI_2022_3171983 crossref_primary_10_1109_TPAMI_2022_3171983 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-02-01 |
| PublicationDateYYYYMMDD | 2023-02-01 |
| PublicationDate_xml | – month: 02 year: 2023 text: 2023-02-01 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 | 2023 |
| 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 | ref57 ref56 ref59 ref58 Bian (ref48) 2017 ref52 ref55 ref54 Simonyan (ref11) 2014 Kingma (ref96) 2015 Wah (ref91) 2011 ref51 ref50 Lakshminarayanan (ref32) 2017 Higgins (ref86) 2017 Havasi (ref66) 2021 ref47 ref42 Wang (ref41) 2016 ref43 Kopetzki (ref70) 2021 Sensoy (ref33) 2018 ref8 Amersfoort (ref34) 2020 ref7 Liong (ref53) 2020 ref4 Hassani (ref46) 2020 ref100 ref101 Denker (ref65) 1991 Peng (ref6) 2019 Antorán (ref67) 2020 Liu (ref5) 2021 ref36 ref30 Ayub (ref103) 2020 Wang (ref40) 2015 ref38 Kingma (ref85) 2014 Frigyik (ref89) 2010 Blundell (ref29) 2015 ref24 Guo (ref90) 2017 ref26 ref20 ref21 Andrew (ref39) 2013 Kiela (ref49) 2019 ref27 Charpentier (ref22) 2020; 33 Zhang (ref3) 2019 ref13 ref12 ref15 ref14 ref97 ref99 ref10 ref98 Ding (ref62) 2021 ref17 ref16 Bojarski (ref9) 2016 ref19 ref18 Malinin (ref68) 2018; 31 Akaho (ref37) 2006 ref93 ref92 Neal (ref25) 2012; 118 Ranganath (ref28) 2014 ref94 Malinin (ref82) 2018; 31 ref88 Malinin (ref69) 2020 ref87 Han (ref35) 2021 Chen (ref45) 2020 Jøsang (ref75) 2012 Bachman (ref44) 2019 ref84 ref80 ref79 ref108 ref78 ref109 ref106 ref107 ref104 ref74 ref105 ref77 ref102 ref76 ref2 ref1 ref71 Srivastava (ref31) 2014; 15 ref73 ref72 Charpentier (ref83) 2020 ref64 ref63 Heo (ref95) 2018 Moon (ref81) 2020 ref60 MacKay (ref23) 1992 ref61 |
| References_xml | – ident: ref14 doi: 10.1109/CVPR.2012.6247814 – ident: ref104 doi: 10.24963/ijcai.2017/631 – ident: ref1 doi: 10.1145/3474085.3475379 – ident: ref58 doi: 10.1109/TMM.2021.3136094 – ident: ref109 doi: 10.48550/arXiv.1810.04805 – ident: ref17 doi: 10.1007/s00530-010-0182-0 – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: ref31 article-title: Dropout: A simple way to prevent neural networks from overfitting publication-title: J. Mach. Learn. Res. – start-page: 1597 volume-title: Proc. Int. Conf. Mach. Learn. year: 2020 ident: ref45 article-title: A simple framework for contrastive learning of visual representations – ident: ref97 doi: 10.1109/CVPR.2016.645 – start-page: 1083 volume-title: Proc. Int. Conf. Mach. Learn. year: 2015 ident: ref40 article-title: On deep multi-view representation learning – ident: ref8 doi: 10.1038/nature21056 – ident: ref56 doi: 10.1109/TMM.2013.2267205 – ident: ref26 doi: 10.1162/neco.1992.4.3.448 – ident: ref61 doi: 10.1109/ICCV.2019.00631 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Representations year: 2014 ident: ref85 article-title: Auto-encoding variational bayes – ident: ref51 doi: 10.24963/ijcai.2019/524 – start-page: 6402 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 2017 ident: ref32 article-title: Simple and scalable predictive uncertainty estimation using deep ensembles – start-page: 559 volume-title: Adv. Neural Inf. Process. Syst. year: 2019 ident: ref3 article-title: CPM-Nets: Cross partial multi-view networks – ident: ref19 doi: 10.1038/nature08538 – ident: ref4 doi: 10.1109/TPAMI.2013.2296528 – ident: ref93 doi: 10.1109/CVPR.2005.16 – ident: ref63 doi: 10.1109/ICCV.2019.00640 – volume-title: Proc. Int. Conf. Learn. Representations year: 2020 ident: ref69 article-title: Ensemble distribution distillation – ident: ref87 doi: 10.1007/978-3-319-42337-1 – ident: ref21 doi: 10.1016/j.neuron.2019.08.038 – ident: ref105 doi: 10.1109/CVPR.2015.7298655 – ident: ref55 doi: 10.1109/JPROC.2003.817150 – start-page: 1 volume-title: The Caltech-UCSD Birds-200–2011 Dataset year: 2011 ident: ref91 – ident: ref15 doi: 10.1109/CVPR.2019.00713 – ident: ref102 doi: 10.1109/CVPR.2019.01211 – year: 2020 ident: ref53 article-title: AMVNet: Assertion-based multi-view fusion network for lidar semantic segmentation – year: 2016 ident: ref41 article-title: Deep variational canonical correlation analysis – ident: ref24 doi: 10.1002/9780470316870 – start-page: 5707 volume-title: Proc. Int. Conf. Mach. Learn. year: 2021 ident: ref70 article-title: Evaluating robustness of predictive uncertainty estimation: Are dirichlet-based models reliable? – ident: ref18 doi: 10.18653/v1/D15-1303 – volume: 118 volume-title: Bayesian Learning for Neural Networks year: 2012 ident: ref25 – start-page: 853 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 1991 ident: ref65 article-title: Transforming neural-net output levels to probability distributions – start-page: 1 volume-title: Proc. Int. Conf. Learn. Representations year: 2017 ident: ref86 article-title: Beta-VAE: Learning basic visual concepts with a constrained variational framework – year: 2016 ident: ref9 article-title: End to end learning for self-driving cars – ident: ref76 doi: 10.1109/TFUZZ.2017.2659764 – ident: ref80 doi: 10.1109/36.602544 – start-page: 814 volume-title: Proc. Int. Conf. Artif. Intell. Statist. year: 2014 ident: ref28 article-title: Black box variational inference – ident: ref84 doi: 10.1007/978-0-387-45528-0 – ident: ref12 doi: 10.18653/v1/N16-1020 – ident: ref106 doi: 10.1007/978-3-642-33715-4_54 – ident: ref2 doi: 10.1109/CVPR46437.2021.01102 – ident: ref52 doi: 10.1109/TPAMI.2018.2879108 – start-page: 6850 volume-title: Proc. Int. Conf. Mach. Learn. year: 2021 ident: ref5 article-title: One pass late fusion multi-view clustering – year: 2017 ident: ref48 article-title: Revisiting the effectiveness of off-the-shelf temporal modeling approaches for large-scale video classification – ident: ref108 doi: 10.1109/ICMEW.2015.7169757 – start-page: 15535 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 2019 ident: ref44 article-title: Learning representations by maximizing mutual information across views – start-page: 3179 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 2018 ident: ref33 article-title: Evidential deep learning to quantify classification uncertainty – ident: ref99 doi: 10.1609/aaai.v32i1.12292 – ident: ref13 doi: 10.18653/v1/P19-1656 – start-page: 1321 volume-title: Proc. Int. Conf. Mach. Learn. year: 2017 ident: ref90 article-title: On calibration of modern neural networks – start-page: 1 year: 2010 ident: ref89 article-title: Introduction to the Dirichlet distribution and related processes – ident: ref16 doi: 10.1145/1027527.1027661 – start-page: 9690 volume-title: Proc. Int. Conf. Mach. Learn. year: 2020 ident: ref34 article-title: Uncertainty estimation using a single deep deterministic neural network – ident: ref94 doi: 10.1109/ICCV.2011.6126543 – ident: ref72 doi: 10.1111/j.2517-6161.1968.tb00722.x – ident: ref73 doi: 10.1515/9780691214696 – ident: ref43 doi: 10.1007/978-3-030-58621-8_45 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref35 article-title: Trusted multi-view classification – ident: ref74 doi: 10.2172/800792 – start-page: 909 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 2018 ident: ref95 article-title: Uncertainty-aware attention for reliable interpretation and prediction – ident: ref20 doi: 10.1038/s41467-018-05432-w – start-page: 1 volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref66 article-title: Training independent subnetworks for robust prediction – start-page: 5092 volume-title: Proc. Int. Conf. Mach. Learn. year: 2019 ident: ref6 article-title: Comic: Multi-view clustering without parameter selection – ident: ref50 doi: 10.1109/CVPR42600.2020.01271 – start-page: 1 volume-title: Proc. Brit. Mach. Vis. Conf. year: 2020 ident: ref103 article-title: Centroid based concept learning for RGB-D indoor scene classification – ident: ref59 doi: 10.1109/TBME.2019.2899222 – ident: ref10 doi: 10.1109/ICIP.2002.1038076 – ident: ref36 doi: 10.1007/978-1-4612-4380-9_14 – ident: ref47 doi: 10.1609/aaai.v32i1.11945 – ident: ref64 doi: 10.1109/ICRA40945.2020.9197266 – volume: 31 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 2018 ident: ref68 article-title: Predictive uncertainty estimation via prior networks – ident: ref107 doi: 10.1109/CVPR.2016.90 – ident: ref71 doi: 10.1214/aoms/1177698950 – year: 2019 ident: ref49 article-title: Supervised multimodal bitransformers for classifying images and text – start-page: 1225 volume-title: Proc. 15th Int. Conf. Inf. Fusion year: 2012 ident: ref75 article-title: Interpretation and fusion of hyper opinions in subjective logic – ident: ref98 doi: 10.1109/ICME.2018.8486573 – start-page: 4116 volume-title: Proc. Int. Conf. Mach. Learn. year: 2020 ident: ref46 article-title: Contrastive multi-view representation learning on graphs – ident: ref100 doi: 10.1109/TIP.2018.2872629 – start-page: 1356 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 2020 ident: ref83 article-title: Posterior network: Uncertainty estimation without ood samples via density-based pseudo-counts – year: 2006 ident: ref37 article-title: A Kernel method for canonical correlation analysis – ident: ref38 doi: 10.1109/TNN.2007.891186 – ident: ref92 doi: 10.1109/CVPR.2004.383 – ident: ref101 doi: 10.1609/aaai.v33i01.33019176 – year: 1992 ident: ref23 article-title: Bayesian methods for adaptive models – volume-title: Adv. Neural Inf. Process. Syst. year: 2020 ident: ref67 article-title: Depth uncertainty in neural networks – start-page: 1613 volume-title: Proc. Int. Conf. Mach. Learn. year: 2015 ident: ref29 article-title: Weight uncertainty in neural network – year: 2021 ident: ref62 article-title: Cooperative learning for multi-view analysis – volume: 33 start-page: 1356 year: 2020 ident: ref22 article-title: Posterior network: Uncertainty estimation without ood samples via density-based pseudo-counts publication-title: Proc. Adv. Neural Inf. Process. Syst. – ident: ref57 doi: 10.1109/TNNLS.2021.3117403 – start-page: 1 year: 2015 ident: ref96 article-title: Adam: A method for stochastic optimization – ident: ref7 doi: 10.1109/TIP.2017.2651379 – ident: ref30 doi: 10.5555/3045390.3045502 – ident: ref77 doi: 10.1016/0167-8655(96)00039-6 – start-page: 7034 volume-title: Proc. Int. Conf. Mach. Learn. year: 2020 ident: ref81 article-title: Confidence-aware learning for deep neural networks – ident: ref88 doi: 10.1109/ICCV48922.2021.01310 – ident: ref78 doi: 10.1109/MFI.2010.5604480 – start-page: 568 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 2014 ident: ref11 article-title: Two-stream convolutional networks for action recognition in videos – volume: 31 start-page: 1 year: 2018 ident: ref82 article-title: Predictive uncertainty estimation via prior networks publication-title: Proc. Adv. Neural Inf. Process. Syst. – ident: ref60 doi: 10.1038/s41467-021-23774-w – ident: ref42 doi: 10.1109/CVPR.2017.312 – start-page: 1247 volume-title: Proc. Int. Conf. Mach. Learn. year: 2013 ident: ref39 article-title: Deep canonical correlation analysis – ident: ref27 doi: 10.5555/2986459.2986721 – ident: ref54 doi: 10.1007/978-3-662-44415-3_16 – ident: ref79 doi: 10.1016/j.inffus.2005.07.003 |
| SSID | ssj0014503 |
| Score | 2.7382843 |
| Snippet | Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 2551 |
| SubjectTerms | Algorithms Bayes methods Classification Computational modeling Dirichlet problem Estimation Evidential deep learning Heuristic algorithms Learning Model accuracy multi-view learning Reliability Robustness Trustworthiness Uncertainty varitional Dirichlet |
| Title | Trusted Multi-View Classification With Dynamic Evidential Fusion |
| URI | https://ieeexplore.ieee.org/document/9767662 https://www.ncbi.nlm.nih.gov/pubmed/35503823 https://www.proquest.com/docview/2761374260 https://www.proquest.com/docview/2659230878 |
| Volume | 45 |
| WOSCitedRecordID | wos000912386000078&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 Electronic Library (IEL) 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/eLvHCXMwlV3JSsRAEC1UPOjBZdziRgveNJq9k5uiDgo6eBh1bqGTruDAMCOz6O9b1VlQUMFbIJ2Frq7Ue6muegDHyk8yRXHGLjL07QAxslXs5XYcF3FAeCMK0DRxvZedTtzrJY9zcNrUwiCi2XyGZ3xocvl6lM_4V9k5hU4Z8Qd3nm5S1mo1GYMgNCrIhGDIw4lG1AUyTnLefbx8uCMq6HnEUCWxbBbPoTjrcA7sWzwyAiu_Y00Tc9qr_3vbNVipsKW4LBfDOszhsAWrtW6DqNy4BctfmhBuwEWXyy5QC1OLaz_38UMYqUzeRGTsJl7601dxXWrXi1KHlD4MA9Ge8b-2TXhq33Svbu1KV8HO_dCd2qHytCoIOxCDjJzM01FY5E6IRMe0Io8OUBMQyQjLKbdA9NFXviYYJiPFdbKZvwULw9EQd0AkhXaygEikzKNAay-RrkZHF5KYkqsztMCtZzfNq6bjrH0xSA35cJLUGCdl46SVcSw4aa55K1tu_Dl6g6e-GVnNugX7tRHTyisnqScJvEjuyW_BUXOa_ImTJGqIoxmN4Twzt0mMLdgujd_cu14zuz8_cw-WWIy-3NO9DwvT8QwPYDF_n_Yn40NatL340CzaTy4-5Es |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9tAEB6hFKnlQCgUcKHtIvXWGvxYe-0biDZKRIg4pG1u1to7FpFQgohD_35n1g8ViVbiZsnrh3Z2PN_n2ZkP4LMO01xTnHHLHENXIsauToLCTZIykYQ3Yom2ietYTSbJbJbebMDXrhYGEe3mMzzlQ5vLN8tizb_Kzih0qpg_uK8iKQOvrtbqcgYysjrIhGHIx4lItCUyXno2vbm4HhEZDALiqIp4NsvnUKT1OAv2JCJZiZV_o00bdQb9l73vDmw36FJc1MvhLWzgYhf6rXKDaBx5F7b-akO4B-dTLrxAI2w1rvtzjr-FFcvkbUTWcuLXvLoV32r1elErkdKn4U4M1vy37R38GHyfXg7dRlnBLcLIr9xIB0aXhB6IQ8ZeHpg4KgsvQiJkRpNPSzQERXJCc9ovEUMMdWgIiKlYc6VsHu5Db7Fc4CGItDReLolGqiKWxgSp8g16plTElXyTowN-O7tZ0bQdZ_WLu8zSDy_NrHEyNk7WGMeBL90193XTjf-O3uOp70Y2s-7AcWvErPHLVRYogi-Ku_I7cNKdJo_iNIle4HJNYzjTzI0SEwcOauN3927XzPvnn_kJXg-n1-NsPJpcHcEblqavd3gfQ696WOMH2Cweq_nq4aNdun8A1Wrmqg |
| 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=Trusted+Multi-View+Classification+With+Dynamic+Evidential+Fusion&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Han%2C+Zongbo&rft.au=Zhang%2C+Changqing&rft.au=Fu%2C+Huazhu&rft.au=Zhou%2C+Joey+Tianyi&rft.date=2023-02-01&rft.issn=1939-3539&rft.eissn=1939-3539&rft.volume=45&rft.issue=2&rft.spage=2551&rft_id=info:doi/10.1109%2FTPAMI.2022.3171983&rft.externalDBID=NO_FULL_TEXT |
| 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 |