{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T13:05:01Z","timestamp":1780319101647,"version":"3.54.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Science and Technology Program of Sichuan Province","award":["2016CC0016"],"award-info":[{"award-number":["2016CC0016"]}]},{"name":"Science and Technology Program of Sichuan Province","award":["2015GZ0119"],"award-info":[{"award-number":["2015GZ0119"]}]},{"name":"Science and Technology Program of Sichuan Province","award":["2012GZX085"],"award-info":[{"award-number":["2012GZX085"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2926993","type":"journal-article","created":{"date-parts":[[2019,7,7]],"date-time":"2019-07-07T19:03:23Z","timestamp":1562526203000},"page":"91667-91678","source":"Crossref","is-referenced-by-count":2,"title":["A Novel Dynamic Network Pruning via Smooth Initialization and its Potential Applications in Machine Learning Based Security Solutions"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3347-8046","authenticated-orcid":false,"given":"Lei","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"De-An","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiu","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"5","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700789"},{"key":"ref33","article-title":"Convolutional neural networks with low-rank regularization","author":"tai","year":"2015","journal-title":"arXiv 1511 06067"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref31","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2017","journal-title":"arXiv 1712 01887"},{"key":"ref30","first-page":"4335","article-title":"Deep neural network compression with single and multiple level quantization","author":"xu","year":"2018","journal-title":"Proc AAAI"},{"key":"ref37","first-page":"3675","article-title":"Deeprebirth: Accelerating deep neural network execution on mobile devices","author":"li","year":"2018","journal-title":"Proc AAAI"},{"key":"ref36","first-page":"3675","article-title":"Dynamic deep neural networks: Optimizing accuracy-efficiency trade-offs by selective execution","author":"liu","year":"2018","journal-title":"Proc AAAI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2869897"},{"key":"ref34","first-page":"2181","article-title":"Runtime neural pruning","author":"lin","year":"2017","journal-title":"Proc NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2902846"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00821"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2006.01.007"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016089"},{"key":"ref20","article-title":"Stochastic activation pruning for robust adversarial defense","author":"dhillon","year":"2015","journal-title":"arXiv 1803 01442"},{"key":"ref22","article-title":"Pruning filters for efficient convnets","author":"li","year":"2016","journal-title":"arXiv 1608 08710"},{"key":"ref21","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref26","article-title":"Deep compression: Com-pressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2016","journal-title":"Proc ICLR"},{"key":"ref25","article-title":"Variational network quantization","author":"achterhold","year":"0"},{"key":"ref50","article-title":"Depthwise separable convolutions for neural machine translation","author":"kaiser","year":"2017","journal-title":"arXiv 1706 03059"},{"key":"ref51","article-title":"SGDR: Stochastic Gradient Descent with Warm Restarts","author":"loshchilov","year":"2016","journal-title":"arXiv 1608 03983"},{"key":"ref59","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","author":"ye","year":"2018","journal-title":"arXiv 1802 00124"},{"key":"ref58","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219855"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref53","article-title":"Improved regularization of convolutional neural networks with cutout","author":"devries","year":"2017","journal-title":"arXiv 1708 04552"},{"key":"ref52","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2018.2832069"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.04.024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2018.2815155"},{"key":"ref13","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"hu","year":"2016","journal-title":"arXiv 1607 03250"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref15","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"molchanov","year":"2017","journal-title":"arXiv 1611 06440"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref17","article-title":"A novel channel pruning method for deep neural network compression","author":"hu","year":"2018","journal-title":"arXiv 1805 11394"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref19","article-title":"Autopruner: An end-to-end train-able filter pruning method for efficient deep model inference","author":"luo","year":"2018","journal-title":"arXiv 1805 08941"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/01926230701320337"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.1202529"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2374218"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a001859"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2900166"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2898174"},{"key":"ref49","author":"krizhevsky","year":"0","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2855686"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2869827"},{"key":"ref45","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref48","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc ICML"},{"key":"ref47","first-page":"709","article-title":"Learning to prune filters in convolutional neural networks","author":"huang","year":"2016","journal-title":"Proc WACV"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref41","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref43","article-title":"On the importance of single directions for generalization","author":"morcos","year":"2018","journal-title":"arXiv 1803 06959"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08756115.pdf?arnumber=8756115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:40:36Z","timestamp":1628624436000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8756115\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2926993","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}