{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T14:24:54Z","timestamp":1780410294742,"version":"3.54.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society","award":["AC01202101103"],"award-info":[{"award-number":["AC01202101103"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036009"],"award-info":[{"award-number":["62036009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936006"],"award-info":[{"award-number":["61936006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3201602","type":"journal-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:09:16Z","timestamp":1662408556000},"page":"5869-5880","source":"Crossref","is-referenced-by-count":26,"title":["Toward Better Accuracy-Efficiency Trade-Offs: Divide and Co-Training"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1320-4283","authenticated-orcid":false,"given":"Shuai","family":"Zhao","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liguang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6399-292X","authenticated-orcid":false,"given":"Wenxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9817-4065","authenticated-orcid":false,"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6363-1446","authenticated-orcid":false,"given":"Tin Lun","family":"Lam","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref4","first-page":"1","article-title":"Snapshot ensembles: Train 1, get M for free","volume-title":"Proc. ICLR","author":"Huang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-016-9535-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3477.809027"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/095400996116820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37599-7_1"},{"key":"ref9","article-title":"When ensembling smaller models is more efficient than single large models","author":"Kondratyuk","year":"2020","journal-title":"arXiv:2005.00570"},{"key":"ref10","first-page":"1","article-title":"Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification","volume-title":"Proc. ICLR","author":"Ge"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_18"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref16","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref17","first-page":"1","article-title":"Mixed precision training","volume-title":"Proc. ICLR","author":"Micikevicius"},{"key":"ref18","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. NeurIPS","author":"Krizhevsky"},{"key":"ref19","article-title":"Network in network","author":"Lin","year":"2013","journal-title":"arXiv:1312.4400"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref24","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. ICLR","author":"Zoph"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref26","first-page":"1","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref27","article-title":"ResNeSt: Split-attention networks","author":"Zhang","year":"2020","journal-title":"arXiv:2004.08955"},{"issue":"1","key":"ref28","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","first-page":"1","article-title":"Slimmable neural networks","volume-title":"Proc. ICLR","author":"Yu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref31","article-title":"What is collaborative learning","author":"Smith","year":"1992","journal-title":"Collaborative Learning: A Sourcebook for Higher Education"},{"key":"ref32","first-page":"1","article-title":"Collaborative learning for deep neural networks","volume-title":"Proc. NeurIPS","author":"Song"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref34","article-title":"Cooperative learning with visual attributes","author":"Batra","year":"2017","journal-title":"arXiv:1705.05512"},{"key":"ref35","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.668"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960566"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref42","first-page":"1","article-title":"A simple weight decay can improve generalization","volume-title":"Proc. NeurIPS","author":"Krogh"},{"key":"ref43","first-page":"1","article-title":"Three mechanisms of weight decay regularization","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref44","first-page":"1","article-title":"Time matters in regularizing deep networks: Weight decay and data augmentation affect early learning dynamics, matter little near convergence","volume-title":"Proc. NeurIPS","author":"Golatkar"},{"key":"ref45","volume-title":"Cuda Toolkit Documentation v11.1.0","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1996.548872"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref49","first-page":"1","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. ICLR","author":"Laine"},{"key":"ref50","article-title":"Accurate, large minibatch SGD: Training imageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref51","article-title":"Bag of tricks for image classification with convolutional neural networks","author":"He","year":"2018","journal-title":"arXiv:1812.01187"},{"key":"ref52","article-title":"Improved regularization of convolutional neural networks with cutout","author":"Devries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref56","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. ICML","author":"Ioffe"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref58","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the rate of convergence O (1\/k2)","volume-title":"Proc. Doklady USSR","volume":"269","author":"Nesterov"},{"key":"ref59","article-title":"RandAugment: Practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2019","journal-title":"arXiv:1909.13719"},{"key":"ref60","first-page":"1","article-title":"Fixup initialization: Residual learning without normalization","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref61","first-page":"1","article-title":"Fast AutoAugment","volume-title":"Proc. NeurIPS","author":"Lim"},{"key":"ref62","article-title":"Shake-shake regularization","author":"Gastaldi","year":"2017","journal-title":"arXiv:1705.07485"},{"key":"ref63","article-title":"MultiGrain: A unified image embedding for classes and instances","author":"Berman","year":"2019","journal-title":"arXiv:1902.05509"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104117"},{"key":"ref67","first-page":"2688","article-title":"Ensemble methods for object detection","volume-title":"Proc. ECAI","author":"Casado-Garc\u00eda"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref70","volume-title":"Deep Learning Examples for Tensor Cores","year":"2020"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09877850.pdf?arnumber=9877850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:45:53Z","timestamp":1706791553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9877850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3201602","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}