{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:19:42Z","timestamp":1740169182580,"version":"3.37.3"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation of China","doi-asserted-by":"publisher","award":["L182033"],"award-info":[{"award-number":["L182033"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for Central Universities","doi-asserted-by":"publisher","award":["2019PTB-001"],"award-info":[{"award-number":["2019PTB-001"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3008854","type":"journal-article","created":{"date-parts":[[2020,7,13]],"date-time":"2020-07-13T21:54:01Z","timestamp":1594677241000},"page":"126628-126636","source":"Crossref","is-referenced-by-count":0,"title":["Variational Bayesian Group-Level Sparsification for Knowledge Distillation"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7105-4207","authenticated-orcid":false,"given":"Yue","family":"Ming","sequence":"first","affiliation":[]},{"given":"Hao","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Yibo","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7655-9228","authenticated-orcid":false,"given":"Hui","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"3288","article-title":"Bayesian compression for deep learning","author":"louizos","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref32"},{"journal-title":"The MNIST Database of Handwritten Digits","year":"1998","author":"lecun","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2319775"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2980383"},{"key":"ref10","first-page":"3088","article-title":"Structured transforms for small-footprint deep learning","author":"sindhwani","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","author":"denton","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 [cs]"},{"key":"ref13","first-page":"187","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"5","author":"hubara","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref14","first-page":"187","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"zhu","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref15","article-title":"Pruning filters for efficient ConvNets","author":"li","year":"2016","journal-title":"arXiv 1608 08710"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288897"},{"key":"ref18","first-page":"2489","article-title":"Variational dropout sparsifies deep neural networks","author":"molchanov","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.280"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2854918"},{"key":"ref4","first-page":"5811","article-title":"Training quantized nets: A deeper understanding","author":"li","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"7528","article-title":"Knowledge distillation by on-the-fly native ensemble","author":"zhu","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472821"},{"key":"ref6","first-page":"1","article-title":"Model compression via distillation and quantization","author":"polino","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/168304.168306"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2925198"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_21"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00048"},{"key":"ref20","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2946102"},{"key":"ref21","first-page":"1","article-title":"Robust student network learning","volume":"7","author":"guo","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2895330"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946480"},{"key":"ref26","first-page":"2554","article-title":"N2n learning: Network to network compression via policy gradient reinforcement learning","author":"ashok","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","first-page":"2554","article-title":"Faster gaze prediction with dense networks and Fisher pruning","author":"theis","year":"2018","journal-title":"Proc Comput Vis Pattern Recognit"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09139512.pdf?arnumber=9139512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T01:09:37Z","timestamp":1641949777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9139512\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3008854","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}