{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:13Z","timestamp":1792786933357,"version":"4.5.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3703828","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T19:46:54Z","timestamp":1781552814000},"page":"13149-13161","source":"Crossref","is-referenced-by-count":3,"title":["Generalized Kullback\u2013Leibler Divergence Loss"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-7851","authenticated-orcid":false,"given":"Jiequan","family":"Cui","sequence":"first","affiliation":[{"name":"Hefei University of Technology (HFUT)","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beier","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC)","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingshan","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC)","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuotao","family":"Tian","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (HIT)","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-1626","authenticated-orcid":false,"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong (HKU)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-4810","authenticated-orcid":false,"given":"Bei","family":"Yu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong (CUHK), Sha Tin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University (NTU)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology (HFUT)","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref3","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00661"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref11","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00075"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3278694"},{"key":"ref14","first-page":"1565","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref17","article-title":"Improving adversarial robustness requires revisiting misclassified examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"ref22","article-title":"Region rebalance for long-tailed semantic segmentation","author":"Cui","year":"2022"},{"key":"ref23","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2019"},{"key":"ref24","first-page":"2958","article-title":"Adversarial weight perturbation helps robust generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wu","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01543"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01304"},{"key":"ref27","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref30","first-page":"4652","article-title":"Overcoming catastrophic forgetting by incremental moment matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2017"},{"key":"ref31","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2020"},{"key":"ref32","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Croce","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref36","article-title":"Intriguing properties of neural networks","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Szegedy","year":"2014"},{"key":"ref37","article-title":"Towards deep learning models resistant to adversarial attacks","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Madry","year":"2018"},{"key":"ref38","first-page":"4218","article-title":"Improving robustness using generated data","author":"Gowal","year":"2021","journal-title":"Advances Neural Inf. Process. Syst. 34: Annu. Conf. Neural Inf. Process. Syst."},{"key":"ref39","first-page":"36246","article-title":"Better diffusion models further improve adversarial training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0109"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref43","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00297"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2443"},{"key":"ref48","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Romero","year":"2015"},{"key":"ref49","article-title":"Contrastive representation distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref51","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zagoruyko","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref54","first-page":"2765","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref58","article-title":"Long-tailed recognition by routing diverse distribution-aware experts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_15"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00682"},{"key":"ref61","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sohn","year":"2020"},{"key":"ref62","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","year":"2017"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25496"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02197"},{"key":"ref66","first-page":"8093","article-title":"Overfitting in adversarially robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rice","year":"2020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2370"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref70","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref73","article-title":"Decoupling representation and classifier for long-tailed recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kang","year":"2020"},{"key":"ref74","article-title":"Long-tail learning via logit adjustment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Menon","year":"2021"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3174892"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11563882.pdf?arnumber=11563882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:57:31Z","timestamp":1790269051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11563882\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":76,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3703828","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}