{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T20:38:36Z","timestamp":1769373516945,"version":"3.49.0"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DMS-1854434"],"award-info":[{"award-number":["DMS-1854434"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DMS-1952644"],"award-info":[{"award-number":["DMS-1952644"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005144","name":"Qualcomm Faculty Award","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005144","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3105366","type":"journal-article","created":{"date-parts":[[2021,8,16]],"date-time":"2021-08-16T20:21:44Z","timestamp":1629145304000},"page":"115292-115314","source":"Crossref","is-referenced-by-count":10,"title":["Improving Network Slimming With Nonconvex Regularization"],"prefix":"10.1109","volume":"9","author":[{"given":"Kevin","family":"Bui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fredrick","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingyong","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Xin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm125"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOAS388"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2013.05.010"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-015-0045-0"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1137\/16M1084754"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2880454"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aa9383"},{"key":"ref39","volume":"3","author":"shor","year":"2012","journal-title":"Minimization Methods for Non-Differentiable Functions"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1198\/016214501753208942"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1198\/016214501753382273"},{"key":"ref78","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":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518498"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2007.898300"},{"key":"ref31","first-page":"960","article-title":"CAP: Context-aware pruning for semantic segmentation","author":"he","year":"2021","journal-title":"Proc IEEE\/CVF Winter Conf Appl Comput Vis"},{"key":"ref30","first-page":"1","article-title":"Lightweight attention convolutional neural network through network slimming for robust facial expression recognition","author":"ma","year":"2021","journal-title":"Signal Image Video Process"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/09-AOS729"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1236-x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.4310\/CMS.2017.v15.n2.a9"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1109\/TNNLS.2012.2197412","article-title":"$L_{1\/2}$ regularization: A thresholding representation theory and a fast solver","volume":"23","author":"xu","year":"2012","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref60","first-page":"1033","article-title":"Fast image deconvolution using hyper-Laplacian priors","author":"krishnan","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2011.2144605"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2012.10.006"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2468175"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2997524"},{"key":"ref27","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.1016\/j.amc.2021.126168","article-title":"Two-stage image segmentation based on nonconvex $\\ell_{2}-\\ell_{p}$ approximation and thresholding","volume":"403","author":"wu","year":"2021","journal-title":"Appl Math Comput"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1214\/009053604000000256"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s12243-019-00731-9"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1214\/09-AOS683"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.4310\/CMS.2017.v15.n3.a12"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-018-0801-z"},{"key":"ref2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"3177","article-title":"Net-trim: Convex pruning of deep neural networks with performance guarantee","author":"aghasi","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"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 Adv Neural Inf Process Syst"},{"key":"ref24","first-page":"2270","article-title":"Learning the number of neurons in deep networks","author":"alvarez","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"hu","year":"2016","journal-title":"arXiv 1607 03250"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.02.029"},{"key":"ref25","article-title":"The power of sparsity in convolutional neural networks","author":"changpinyo","year":"2017","journal-title":"arXiv 1702 06257"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00804"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20124"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref92","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1137\/140952363"},{"key":"ref90","first-page":"360","article-title":"Convergence of a relaxed variable splitting method for learning sparse neural networks via $\\ell_{1}$ , $\\ell_{0}$ , and transformed-$\\ell_{1}$ penalties","author":"dinh","year":"2020","journal-title":"Proc SAI Intell Syst Conf"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3724\/SP.J.1004.2012.01225"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/24\/3\/035020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18161-5_15"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-014-9930-1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.21391"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/52\/11\/018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1137\/070703983"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.862083"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref40","first-page":"39","article-title":"Nonconvex regularization for network slimming: Compressing CNNs even more","author":"bui","year":"2020","journal-title":"Proc Int Symp Vis Comput"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.78"},{"key":"ref13","article-title":"Trained rank pruning for efficient deep neural networks","author":"xu","year":"2018","journal-title":"arXiv 1812 02402"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/136"},{"key":"ref15","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","author":"chen","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref16","first-page":"3123","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref81","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref17","article-title":"Ternary weight networks","author":"li","year":"2016","journal-title":"arXiv 1605 04711 [cs]"},{"key":"ref84","first-page":"1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","article-title":"Trained ternary quantization","author":"zhu","year":"2016","journal-title":"arXiv 1612 01064"},{"key":"ref83","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/18M1166134"},{"key":"ref80","volume":"266","author":"penot","year":"2012","journal-title":"Calculus Without Derivatives"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94463-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref3","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref85","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS Workshop Deep Learn Unsupervised Feature Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2020.529564"},{"key":"ref87","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref9","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","first-page":"800","article-title":"Learning sparse neural networks via $\\ell_{0}$ and $\\text{T}\\ell_{1}$ by a relaxed variable splitting method with application to multi-scale curve classification","author":"xue","year":"2019","journal-title":"Proc World Congr Global Optim"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3058672"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.08.015"},{"key":"ref42","article-title":"ProxQuant: Quantized neural networks via proximal operators","author":"bai","year":"2018","journal-title":"arXiv 1810 00861"},{"key":"ref41","article-title":"Convolutional neural networks with low-rank regularization","author":"tai","year":"2015","journal-title":"arXiv 1511 06067"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/19M1246468"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09514866.pdf?arnumber=9514866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T12:37:13Z","timestamp":1699360633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9514866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3105366","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}