{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,18]],"date-time":"2025-05-18T04:02:49Z","timestamp":1747540969226,"version":"3.40.5"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","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"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["RS-2024-00398948"],"award-info":[{"award-number":["RS-2024-00398948"]}]},{"name":"2024 Innovation Base Artificial Intelligence Data Convergence","award":["S2201-24-1002"],"award-info":[{"award-number":["S2201-24-1002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/jstsp.2025.3546083","type":"journal-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T18:46:55Z","timestamp":1740768415000},"page":"491-506","source":"Crossref","is-referenced-by-count":0,"title":["Deep Minimax Classifiers for Imbalanced Datasets With a Small Number of Minority Samples"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4269-6820","authenticated-orcid":false,"given":"Hansung","family":"Choi","sequence":"first","affiliation":[{"name":"Electrical Engineering and Computer Science, DGIST, Daegu, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0509-5278","authenticated-orcid":false,"given":"Daewon","family":"Seo","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science, DGIST, Daegu, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3046439"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01517"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref5","first-page":"1567","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao","year":"2019"},{"key":"ref6","article-title":"Long-tail learning via logit adjustment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Menon","year":"2021"},{"article-title":"Identifying and compensating for feature deviation in imbalanced deep learning","year":"2020","author":"Ye","key":"ref7"},{"key":"ref8","first-page":"18970","article-title":"Label-imbalanced and group-sensitive classification under overparameterization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kini","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3047335"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref11","first-page":"872","article-title":"What is the effect of importance weighting in deep learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Byrd","year":"2019"},{"key":"ref12","article-title":"CUDA: Curriculum of data augmentation for long-tailed recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ahn","year":"2023"},{"key":"ref13","first-page":"15696","article-title":"Large language models struggle to learn long-tail knowledge","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kandpal","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3136503"},{"key":"ref15","first-page":"65583","article-title":"Neural collapse to multiple centers for imbalanced data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yan","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01518"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02306"},{"key":"ref18","article-title":"Delving into semantic scale imbalance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2023"},{"key":"ref19","first-page":"27542","article-title":"Feature directions matter: Long-tailed learning via rotated balanced representation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peifeng","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02208"},{"key":"ref21","first-page":"28204","article-title":"Enhancing class-imbalanced learning with pre-trained guidance through class-conditional knowledge distillation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29260"},{"key":"ref23","first-page":"8082","article-title":"Class-imbalanced semi-supervised learning with adaptive thresholding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2022"},{"key":"ref24","first-page":"22791","article-title":"Escaping saddle points for effective generalization on class-imbalanced data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rangwani","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01042"},{"key":"ref26","first-page":"79909","article-title":"Revive re-weighting in imbalanced learning by density ratio estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Luo","year":"2024"},{"key":"ref27","first-page":"48417","article-title":"A unified generalization analysis of re-weighting and logit-adjustment for imbalanced learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"volume-title":"Van Trees, Detection, Estimation, and Modulation Theory.","year":"1968","author":"H","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2341-0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3061298"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26749"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.05.007"},{"key":"ref33","first-page":"103","article-title":"Minimax regret classifier for imprecise class distributions","volume":"8","author":"Alaiz-Rodriguez","year":"2007","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sagawa","year":"2020"},{"key":"ref35","article-title":"Coping with label shift via distributionally robust optimisation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2021"},{"key":"ref36","article-title":"Distributionally robust post-hoc classifiers under prior shifts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei","year":"2023"},{"key":"ref37","article-title":"Revisiting adversarial training for the worst-performing class","author":"Pethick","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1017\/9781108679930"},{"journal-title":"Appl. Nonlinear Anal.","year":"2006","author":"Aubin","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2015509117"},{"key":"ref42","first-page":"16927","article-title":"Bayes consistency vs. H-consistency: The interplay between surrogate loss functions and the scoring function class","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2020"},{"article-title":"Multiclass classification calibration functions","year":"2016","author":"Pires","key":"ref43"},{"key":"ref44","first-page":"1117","article-title":"H-consistency bounds for surrogate loss minimizers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Awasthi","year":"2022"},{"key":"ref45","first-page":"46903","article-title":"Structured prediction with stronger consistency guarantees","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mao","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2208779120"},{"key":"ref47","first-page":"4334","article-title":"Learning to reweight examples for robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ren","year":"2018"},{"key":"ref48","article-title":"Improving the accuracy of learning example weights for imbalance classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref49","first-page":"3163","article-title":"AutoBalance: Optimized loss functions for imbalanced data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"issue":"86","key":"ref52","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"volume-title":"Foundations of Machine Learning.","year":"2018","author":"Mohri","key":"ref53"},{"article-title":"Handbook of convergence theorems for (stochastic) gradient methods","year":"2023","author":"Garrigos","key":"ref54"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11006305\/10908081.pdf?arnumber=10908081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T04:49:31Z","timestamp":1747457371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10908081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":54,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3546083","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}