{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:41:34Z","timestamp":1784302894806,"version":"3.55.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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","doi-asserted-by":"publisher","award":["62206108"],"award-info":[{"award-number":["62206108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Maritime AI Research Programme","award":["SMI-2022-MTP-06"],"award-info":[{"award-number":["SMI-2022-MTP-06"]}]},{"name":"AI Singapore OTTC","award":["AISG2-TC-2022-006"],"award-info":[{"award-number":["AISG2-TC-2022-006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tpami.2023.3290544","type":"journal-article","created":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T17:23:51Z","timestamp":1688059431000},"page":"1-15","source":"Crossref","is-referenced-by-count":15,"title":["Data-Efficient Learning via Minimizing Hyperspherical Energy"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7391-0334","authenticated-orcid":false,"given":"Xiaofeng","family":"Cao","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8234-3263","authenticated-orcid":false,"given":"Weiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Cambridge, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2211-8176","authenticated-orcid":false,"given":"Ivor W.","family":"Tsang","sequence":"additional","affiliation":[{"name":"Centre for Frontier AI Research, and the Institute of High-Performance Computing, Agency for Science, Technology and Research (A*STAR), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00617"},{"key":"ref57","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"gretton","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref56","first-page":"105","article-title":"Transfer learning by distribution matching for targeted advertising","author":"bickel","year":"2008","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","first-page":"199","article-title":"Agnostic active learning without constraints","author":"beygelzimer","year":"2010","journal-title":"Proc 23rd Int Conf Neural Inf Process Syst"},{"key":"ref59","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"liang","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","article-title":"Finding the homology of decision boundaries with active learning","author":"li","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2874458"},{"key":"ref53","first-page":"1","article-title":"Spherical k-means clustering","volume":"50","author":"buchta","year":"2012","journal-title":"J Statist Softw"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3093590"},{"key":"ref11","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","author":"xie","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390182"},{"key":"ref10","first-page":"1183","article-title":"Deep Bayesian active learning with image data","author":"gal","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","first-page":"2801","article-title":"Region-based active learning","author":"cortes","year":"2019","journal-title":"Proc 22nd Int Conf Artif Intell Statist"},{"key":"ref17","article-title":"Efficient active learning","author":"beygelzimer","year":"2011","journal-title":"Proc ICML Workshop On-line Trading Exploration Exploitation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273541"},{"key":"ref19","first-page":"379","article-title":"Relating clustering stability to properties of cluster boundaries","author":"ben-david","year":"2008","journal-title":"Proc 21st Annu Conf Learn Theory"},{"key":"ref18","first-page":"6222","article-title":"Learning towards minimum hyperspherical energy","author":"liu","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783364"},{"key":"ref50","article-title":"Neural similarity learning","author":"liu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00717"},{"key":"ref48","article-title":"Rethinking softmax cross-entropy loss for adversarial robustness","author":"pang","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2357"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053424"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00695"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2990277"},{"key":"ref43","first-page":"727","article-title":"Impact of minimum hyperspherical energy regularization on time-frequency domain networks for singing voice separation","author":"shah","year":"2020","journal-title":"Proc Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref49","article-title":"Hyperspherical prototype networks","author":"mettes","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7471613"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref4","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367572"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.39"},{"key":"ref40","first-page":"6393","article-title":"Differentiating through the Fréchet mean","author":"lou","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","first-page":"1180","article-title":"Learning with hyperspherical uniformity","author":"liu","year":"2021","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2007.911292"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.89.185502"},{"key":"ref78","first-page":"801","article-title":"On the generalization ability of online strongly convex programming algorithms","author":"kakade","year":"2008","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref37","first-page":"3950","article-title":"Deep hyperspherical learning","author":"liu","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/0222052"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01096"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2591796.2591839"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.696"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1214\/009053606000000786"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(00)00089-X"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116829"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref2","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref39","first-page":"1637","article-title":"Angular visual hardness","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00293"},{"key":"ref71","first-page":"7026","article-title":"BatchBALD: Efficient and diverse batch acquisition for deep Bayesian active learning","author":"kirsch","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref70","year":"2023"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623760"},{"key":"ref72","first-page":"334","article-title":"Towards safe weakly supervised learning","volume":"43","author":"li","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref24","first-page":"441","article-title":"Toward optimal active learning through Monte Carlo estimation of error reduction","author":"roy","year":"2001","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015117"},{"key":"ref23","first-page":"1379","article-title":"Active learning with disagreement graphs","author":"cortes","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2496974"},{"key":"ref26","first-page":"442","article-title":"Beyond disagreement-based agnostic active learning","author":"zhang","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2008.07.003"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3016928"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027605"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_9"},{"key":"ref22","first-page":"2144","article-title":"Adaptive region-based active learning","author":"cortes","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143980"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1561\/2200000037"},{"key":"ref65","first-page":"45","article-title":"Support vector machine active learning with applications to text classification","volume":"2","author":"tong","year":"2001","journal-title":"J Mach Learn Res"},{"key":"ref28","first-page":"1999","article-title":"Sufficient conditions for agnostic active learnable","author":"wang","year":"2009","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref27","first-page":"2755","article-title":"Efficient and parsimonious agnostic active learning","author":"huang","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553381"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390183"},{"key":"ref62","article-title":"Bayesian active learning for classification and preference learning","author":"houlsby","year":"2011"},{"key":"ref61","article-title":"Active learning for convolutional neural networks: A core-set approach","author":"sener","year":"2018","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/10168255.pdf?arnumber=10168255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T15:12:10Z","timestamp":1696432330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10168255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3290544","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":[[2023]]}}}