{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:44:55Z","timestamp":1757313895572,"version":"3.37.3"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0107400"],"award-info":[{"award-number":["2020AAA0107400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20222"],"award-info":[{"award-number":["U20A20222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LR19F020004"],"award-info":[{"award-number":["LR19F020004"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Scientific Technological Innovation Research Project by Ministry of Education"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tnnls.2021.3107317","type":"journal-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T19:53:41Z","timestamp":1632340421000},"page":"2647-2658","source":"Crossref","is-referenced-by-count":5,"title":["Elastic Knowledge Distillation by Learning From Recollection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1650-7167","authenticated-orcid":false,"given":"Yongjian","family":"Fu","sequence":"first","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songyuan","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-4534","authenticated-orcid":false,"given":"Hanbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenfu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihao","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijie","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3023-1662","authenticated-orcid":false,"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511569920.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00297"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5859"},{"key":"ref4","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"arXiv:1610.02242","author":"Laine","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015628"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref8","article-title":"FitNets: Hints for thin deep nets","volume-title":"arXiv:1412.6550","author":"Romero","year":"2014"},{"key":"ref9","first-page":"2654","article-title":"Do deep nets really need to be deep","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ba"},{"key":"ref10","article-title":"Distilling the knowledge in a neural network","volume-title":"arXiv:1503.02531","author":"Hinton","year":"2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref12","first-page":"5142","article-title":"Towards understanding knowledge distillation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Phuong"},{"key":"ref13","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello"},{"key":"ref14","article-title":"Unifying distillation and privileged information","volume-title":"arXiv:1511.03643","author":"Lopez-Paz","year":"2015"},{"key":"ref15","article-title":"Understanding and improving knowledge distillation","volume-title":"arXiv:2002.03532","author":"Tang","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851924"},{"key":"ref17","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"arXiv:1612.03928","author":"Zagoruyko","year":"2016"},{"key":"ref18","first-page":"2888","article-title":"Moonshine: Distilling with cheap convolutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Crowley"},{"key":"ref19","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","volume-title":"arXiv:1707.01219","author":"Huang","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00067"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref25","first-page":"1","article-title":"Contrastive representation distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tian"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref27","first-page":"775","article-title":"KDGAN: Knowledge distillation with generative adversarial networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref28","article-title":"Training shallow and thin networks for acceleration via knowledge distillation with conditional adversarial networks","volume-title":"arXiv:1709.00513","author":"Xu","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013771"},{"key":"ref30","first-page":"9547","article-title":"Zero-shot knowledge transfer via adversarial belief matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Micaelli"},{"key":"ref31","first-page":"7517","article-title":"Knowledge distillation by on-the-fly native ensemble","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00433"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref40","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.","author":"Tarvainen"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"article-title":"The Caltech-UCSD birds-200-2011 dataset","year":"2011","author":"Wah","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10114428\/09546048.pdf?arnumber=9546048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:03:21Z","timestamp":1705017801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9546048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":44,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3107317","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}