{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T21:01:58Z","timestamp":1784667718285,"version":"3.55.0"},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China NSFC","doi-asserted-by":"crossref","award":["T2525004"],"award-info":[{"award-number":["T2525004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China NSFC","doi-asserted-by":"crossref","award":["62272298"],"award-info":[{"award-number":["62272298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Noncommunicable Chronic Diseases\u2013National Science and Technology Major Project","award":["2023ZD0509202"],"award-info":[{"award-number":["2023ZD0509202"]}]},{"name":"Noncommunicable Chronic Diseases\u2013National Science and Technology Major Project","award":["2023ZD0509201"],"award-info":[{"award-number":["2023ZD0509201"]}]},{"name":"National Key Research and Development Program of China","award":["2022YFC2407000"],"award-info":[{"award-number":["2022YFC2407000"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3661760","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:52:22Z","timestamp":1770411142000},"page":"7588-7599","source":"Crossref","is-referenced-by-count":10,"title":["Contrastive Decoupling: Dynamic Regularization for Enhanced Fine-Grained Image Classification"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3255-8573","authenticated-orcid":false,"given":"Zheyuan","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3844-0522","authenticated-orcid":false,"given":"Tingyao","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Qin","sequence":"additional","affiliation":[{"name":"Beijing Visual Science and Translational Eye Research Institute (BERI), School of Clinical Medicine, Tsinghua Medicine, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8678-2784","authenticated-orcid":false,"given":"Bin","family":"Sheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3168787"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3340225"},{"key":"ref3","article-title":"Learning clustering-based prototypes for compositional zero-shot learning","author":"Qu","year":"2025","journal-title":"arXiv:2502.06501"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3586118"},{"key":"ref5","article-title":"Locality-aware cross-modal correspondence learning for dense audio-visual events localization","author":"Xing","year":"2024","journal-title":"arXiv:2409.07967"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3275382"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284405"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3227737"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248791"},{"key":"ref13","article-title":"Bird species categorization using pose normalized deep convolutional nets","author":"Branson","year":"2014","journal-title":"arXiv:1406.2952"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298775"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.129"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6912"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355461"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref26","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3244340"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3535818"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3523802"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16255"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01182"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01583"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref38","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref40","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref41","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Chen"},{"key":"ref42","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref45","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref46","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res. J."},{"key":"ref47","article-title":"DINOv3","author":"Simeoni","year":"2025","journal-title":"arXiv:2508.10104"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref49","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Khosla"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01455"},{"issue":"285","key":"ref52","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Otsu","year":"1975","journal-title":"Automatica"},{"key":"ref53","article-title":"The caltech-ucsd birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref55","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"issue":"1","key":"ref56","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop Fine-Grained Vis. Categorization (FGVC)","volume":"2","author":"Khosla"},{"key":"ref57","volume-title":"APTOS 2019 Blindness Detection","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101561"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2013.1743"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01388-1"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0207982"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2921876"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3114622"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055617"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01483"},{"key":"ref69","first-page":"11162","article-title":"Vit-Net: Interpretable vision transformers with neural tree decoder","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00156"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109979"},{"key":"ref72","first-page":"2570","article-title":"Delving into multimodal prompting for fine-grained visual classification","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Xin"},{"key":"ref73","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref75","article-title":"Co-mixup: Saliency guided joint mixup with supermodular diversity","author":"Kim","year":"2021","journal-title":"arXiv:2102.03065"},{"key":"ref76","article-title":"SaliencyMix: A saliency guided data augmentation strategy for better regularization","author":"Shahab Uddin","year":"2020","journal-title":"arXiv:2006.01791"},{"key":"ref77","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Kim"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_26"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref81","volume-title":"Pytorch Image Models","author":"Wightman","year":"2019"},{"key":"ref82","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref85","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Sohn"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-025-01365-0"},{"key":"ref87","first-page":"1059","article-title":"High-performance large-scale image recognition without normalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brock"},{"key":"ref88","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen"},{"key":"ref89","first-page":"5049","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref90","article-title":"Remixmatch: Semi-supervised learning with distribution matching and augmentation anchoring","volume-title":"Proc. ICLR","author":"Kurakin","year":"2020"},{"key":"ref91","first-page":"11525","article-title":"Dash: Semi-supervised learning with dynamic thresholding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref92","first-page":"10065","article-title":"Sinkhorn label allocation: Semi-supervised classification via annealed self-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tai"},{"key":"ref93","first-page":"22919","article-title":"NP-Match: When neural processes meet semi-supervised learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01407"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3441813"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11373253.pdf?arnumber=11373253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:37Z","timestamp":1780948477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11373253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":97,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3661760","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}