{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T15:49:21Z","timestamp":1773848961409,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62141412"],"award-info":[{"award-number":["62141412"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61872201"],"award-info":[{"award-number":["61872201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Plan of Tianjin","award":["20JCZDJC00610"],"award-info":[{"award-number":["20JCZDJC00610"]}]},{"name":"Key Research and Development Program of Guangdong","award":["2021B0101310002"],"award-info":[{"award-number":["2021B0101310002"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tnnls.2022.3164264","type":"journal-article","created":{"date-parts":[[2022,4,14]],"date-time":"2022-04-14T19:34:03Z","timestamp":1649964843000},"page":"10051-10064","source":"Crossref","is-referenced-by-count":20,"title":["STKD: Distilling Knowledge From Synchronous Teaching for Efficient Model Compression"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4021-6466","authenticated-orcid":false,"given":"Tongtong","family":"Su","sequence":"first","affiliation":[{"name":"TJ Key Laboratory of NDST, College of Computer Science, Nankai University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6238-7931","authenticated-orcid":false,"given":"Jinsong","family":"Zhang","sequence":"additional","affiliation":[{"name":"TJ Key Laboratory of NDST, College of Computer Science, Nankai University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2450-4997","authenticated-orcid":false,"given":"Zhaoyang","family":"Yu","sequence":"additional","affiliation":[{"name":"TJ Key Laboratory of NDST, College of Computer Science, Nankai University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0387-2501","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"TJ Key Laboratory of NDST, College of Computer Science, Nankai University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9010-3278","authenticated-orcid":false,"given":"Xiaoguang","family":"Liu","sequence":"additional","affiliation":[{"name":"TJ Key Laboratory of NDST, College of Computer Science, Nankai University, Tianjin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298685"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00990"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2749125"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2791721"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref9","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref13","first-page":"7517","article-title":"Knowledge distillation by on-the-fly native ensemble","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref14","first-page":"875","article-title":"Discrimination-aware channel pruning for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhuang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00826"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2873305"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref18","article-title":"Learning from a lightweight teacher for efficient knowledge distillation","author":"Liu","year":"2020","journal-title":"arXiv:2005.09163"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref20","first-page":"1","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Romero"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref22","article-title":"Residual knowledge distillation","author":"Gao","year":"2020","journal-title":"arXiv:2002.09168"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00069"},{"key":"ref25","first-page":"1","article-title":"Large scale distributed neural network training through online distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Anil"},{"key":"ref26","first-page":"1832","article-title":"Collaborative learning for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref28","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Chen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref31","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zagoruyko"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00710"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref34","first-page":"2760","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref35","article-title":"Preparing lessons: Improve knowledge distillation with better supervision","author":"Wen","year":"2019","journal-title":"arXiv:1911.07471"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00153"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref39","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","author":"Mishra","year":"2017","journal-title":"arXiv:1711.05852"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/291"},{"key":"ref41","article-title":"Model compression via distillation and quantization","author":"Polino","year":"2018","journal-title":"arXiv:1802.05668"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00206"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01206"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11601"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5746"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.62"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01103"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0700-1"},{"key":"ref50","first-page":"1","article-title":"Feature-level ensemble knowledge distillation for aggregating knowledge from multiple networks","volume-title":"Proc. ECAI","author":"Park"},{"key":"ref51","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"Huang","year":"2017","journal-title":"arXiv:1707.01219"},{"key":"ref52","article-title":"Understanding and improving knowledge distillation","author":"Tang","year":"2020","journal-title":"arXiv:2002.03532"},{"key":"ref53","first-page":"5142","article-title":"Towards understanding knowledge distillation","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Mai"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2953106"},{"key":"ref55","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref56","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshops","author":"Netzer"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref61","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3007506"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412615"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref67","article-title":"Training shallow and thin networks for acceleration via knowledge distillation with conditional adversarial networks","author":"Xu","year":"2017","journal-title":"arXiv:1709.00513"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10336252\/09757208.pdf?arnumber=9757208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:08:25Z","timestamp":1708110505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9757208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":67,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3164264","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}