{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T19:24:34Z","timestamp":1773775474963,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3389676","type":"journal-article","created":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T13:30:55Z","timestamp":1714570255000},"page":"6544-6555","source":"Crossref","is-referenced-by-count":9,"title":["Learning With Noisy Labels Over Imbalanced Subpopulations"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7822-4651","authenticated-orcid":false,"given":"Mingcai","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8179-4903","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"given":"Bing","family":"He","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"given":"Zongbo","family":"Han","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9548-1227","authenticated-orcid":false,"given":"Junzhou","family":"Huang","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering Department, University of Texas at Arlington, Arlington, TX, USA"}]},{"given":"Bingzhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9157-9596","authenticated-orcid":false,"given":"Jianhua","family":"Yao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx044"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inform. Process. Syst. (NIPS)","author":"Vaswani"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref5","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/bf00116829"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/TNNLS.2023.3291695","article-title":"Separating noisy samples from tail classes for long-tailed image classification with label noise","author":"Fang","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref8","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"Reed","year":"2014","journal-title":"arXiv:1412.6596"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref10","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","author":"Li","year":"2020","journal-title":"arXiv:2002.07394"},{"key":"ref11","first-page":"1","article-title":"BREEDS: Benchmarks for subpopulation shift","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Santurkar"},{"key":"ref12","first-page":"6602","article-title":"Multi-objective interpolation training for robustness to label noise","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Ortego"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00463"},{"key":"ref14","first-page":"2034","article-title":"Does distributionally robust supervised learning give robust classifiers?","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Hu"},{"key":"ref15","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","author":"Sagawa","year":"2019","journal-title":"arXiv:1911.08731"},{"key":"ref16","first-page":"2304","article-title":"MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref17","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref18","first-page":"5907","article-title":"SELFIE: Refurbishing unclean samples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref19","first-page":"28","article-title":"Robust curriculum learning: From clean label detection to noisy label self-correction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00013"},{"key":"ref21","article-title":"A topological filter for learning with label noise","author":"Wu","year":"2020","journal-title":"arXiv:2012.04835"},{"key":"ref22","first-page":"24137","article-title":"FINE samples for learning with noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Kim"},{"key":"ref23","first-page":"3355","article-title":"Dimensionality-driven learning with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68474-1_5"},{"key":"ref25","article-title":"Selective-supervised contrastive learning with noisy labels","author":"Li","year":"2022","journal-title":"arXiv:2203.04181"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_42"},{"key":"ref27","article-title":"Robust long-tailed learning under label noise","author":"Wei","year":"2021","journal-title":"arXiv:2108.11569"},{"key":"ref28","article-title":"Combating noisy-labeled and imbalanced data by two stage bi-dimensional sample selection","author":"Lu","year":"2022","journal-title":"arXiv:2208.09833"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445915"},{"key":"ref30","first-page":"1","article-title":"Learning with noisy labels revisited: A study using real-world human annotations","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Wei"},{"key":"ref31","first-page":"1934","article-title":"Fairness without demographics in repeated loss minimization","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Hashimoto"},{"key":"ref32","first-page":"1","article-title":"Distributionally robust neural networks","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Sagawa"},{"key":"ref33","first-page":"1","article-title":"Coping with label shift via distributionally robust optimisation","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref34","first-page":"12857","article-title":"Examining and combating spurious features under distribution shift","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Zhou"},{"key":"ref35","first-page":"25407","article-title":"Improving out-of-distribution robustness via selective augmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Yao"},{"key":"ref36","first-page":"6781","article-title":"Just train twice: Improving group robustness without training group information","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Liu"},{"key":"ref37","article-title":"Learning from failure: Training debiased classifier from biased classifier","author":"Nam","year":"2020","journal-title":"arXiv:2007.02561"},{"key":"ref38","first-page":"26484","article-title":"Correct-N-Contrast: A contrastive approach for improving robustness to spurious correlations","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Zhang"},{"key":"ref39","first-page":"2189","article-title":"Environment inference for invariant learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Creager"},{"key":"ref40","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019","journal-title":"arXiv:1907.02893"},{"key":"ref41","first-page":"1","article-title":"Spread spurious attribute: Improving worst-group accuracy with spurious attribute estimation","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Nam"},{"key":"ref42","first-page":"1","article-title":"AGRO: Adversarial discovery of error-prone groups for robust optimization","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Paranjape"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143868"},{"key":"ref44","first-page":"19339","article-title":"No subclass left behind: Fine-grained robustness in coarse-grained classification problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohoni"},{"key":"ref45","first-page":"12345","article-title":"DORO: Distributional and outlier robust optimization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Zhai"},{"key":"ref46","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","author":"Sohn","year":"2020","journal-title":"arXiv:2001.07685"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref49","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref50","article-title":"WebVision database: Visual learning and understanding from web data","author":"Li","year":"2017","journal-title":"arXiv:1708.02862"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3125459"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref53","first-page":"9964","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","first-page":"19934","article-title":"Earlylearning regularization prevents memorization of noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247629"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00519"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01909"},{"key":"ref59","article-title":"A survey of label-noise representation learning: Past, present and future","author":"Han","year":"2020","journal-title":"arXiv:2011.04406"},{"key":"ref60","first-page":"1062","article-title":"Understanding and utilizing deep neural networks trained with noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02305"},{"key":"ref63","first-page":"2688","article-title":"Boosting Co-teaching with compression regularization for label noise","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Chen"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00793"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10516662.pdf?arnumber=10516662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:20Z","timestamp":1765219280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10516662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":64,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3389676","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}