{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:33:21Z","timestamp":1787013201432,"version":"3.56.0"},"reference-count":66,"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":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY20F020023"],"award-info":[{"award-number":["LY20F020023"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1866602"],"award-info":[{"award-number":["U1866602"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key RD Program of China","award":["2019YFB1600700"],"award-info":[{"award-number":["2019YFB1600700"]}]},{"name":"Starry Night Science Fund of Zhejiang University Shanghai Institute for Advanced Study","award":["SN-ZJU-SIAS-001"],"award-info":[{"award-number":["SN-ZJU-SIAS-001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tkde.2022.3171571","type":"journal-article","created":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T16:14:47Z","timestamp":1651594487000},"page":"1-1","source":"Crossref","is-referenced-by-count":23,"title":["SemCKD: Semantic Calibration for Cross-Layer Knowledge Distillation"],"prefix":"10.1109","author":[{"given":"Can","family":"Wang","sequence":"first","affiliation":[{"name":"College of Computer Science, Zhejiang University, 12377 Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Defang","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, 12377 Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-Ping","family":"Mei","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, 12624 Hangzhou, Zhejiang, China, 310014"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, 12377 Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Feng","sequence":"additional","affiliation":[{"name":"Colledge of Computer Science, Zhejiang University, 12377 Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, 12377 Hangzhou, Zhejiang, China, 310058"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref14","article-title":"When does label smoothing help?","author":"m\u00fcller","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref53","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref52","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref11","article-title":"Model compression via distillation and quantization","author":"polino","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref10","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.128"},{"key":"ref17","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","article-title":"FitNets: Hints for thin deep nets","author":"romero","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref51","author":"bertsekas","year":"2014","journal-title":"Constrained Optimization and Lagrange Multiplier Methods"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.56021\/9781421407944"},{"key":"ref46","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref48","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref42","article-title":"Contrastive representation distillation","author":"tian","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref8","first-page":"2148","article-title":"Predicting parameters in deep learning","author":"denil","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref3","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref6","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00726"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_28"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5746"},{"key":"ref37","first-page":"3030","article-title":"Learning what and where to transfer","author":"jang","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","first-page":"5072","article-title":"Transfer learning via learning to transfer","author":"wei","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref30","first-page":"442","article-title":"Tensorizing neural networks","author":"novikov","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","article-title":"Large scale distributed neural network training through online distillation","author":"anil","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","article-title":"Pruning filters for efficient ConvNets","author":"li","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/bs.3830070216"},{"key":"ref23","first-page":"3519","article-title":"Similarity of neural network representations revisited","author":"kornblith","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289451"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00241"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref66","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"goyal","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_19"},{"key":"ref65","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747534"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref62","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/4358933\/09767633.pdf?arnumber=9767633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T20:22:42Z","timestamp":1682972562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9767633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tkde.2022.3171571","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}