{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T01:23:41Z","timestamp":1768872221511,"version":"3.49.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Natural Key R&amp;D Program of China","award":["2017YFB1002400"],"award-info":[{"award-number":["2017YFB1002400"]}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY16F010004"],"award-info":[{"award-number":["LY16F010004"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013223","name":"Chongqing Research Program of Basic Research and Frontier Technology","doi-asserted-by":"publisher","award":["cstc2016jcyjA0542"],"award-info":[{"award-number":["cstc2016jcyjA0542"]}],"id":[{"id":"10.13039\/501100013223","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/jstsp.2019.2961233","type":"journal-article","created":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T05:08:35Z","timestamp":1577164115000},"page":"775-788","source":"Crossref","is-referenced-by-count":27,"title":["Structured Pruning for Efficient Convolutional Neural Networks via Incremental Regularization"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-901X","authenticated-orcid":false,"given":"Huan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyi","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5084-0572","authenticated-orcid":false,"given":"Yuehai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2903-9913","authenticated-orcid":false,"given":"Lu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6048-6549","authenticated-orcid":false,"given":"Haoji","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref71","first-page":"317","article-title":"Data-driven sparse structure selection for deep neural networks","author":"huang","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref39","article-title":"BinaryNet: Training deep neural networks with weights and activations constrained to +1 or ?1","author":"courbariaux","year":"2016"},{"key":"ref38","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref32","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size","author":"iandola","year":"2016"},{"key":"ref31","first-page":"6775","article-title":"Structured Bayesian pruning via log-normal multiplicative noise","author":"neklyudov","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","author":"molchanov","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"7005","article-title":"LegoNet: Efficient convolutional neural networks with Lego filters","author":"yang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","first-page":"122","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","author":"ma","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref60","first-page":"1","article-title":"Speeding up convolutional neural networks with low rank expansions","author":"jaderberg","year":"0","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298809"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref28","first-page":"149","article-title":"Structured probabilistic pruning for convolutional neural network acceleration","author":"wang","year":"0","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref64","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref27","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","first-page":"3288","article-title":"Bayesian compression for deep learning","author":"louizos","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","first-page":"1","article-title":"Rethinking the value of network pruning","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref68","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref69","article-title":"Autopruner: An end-to-end trainable filter pruning method for efficient deep model inference","author":"luo","year":"2018"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852463"},{"key":"ref20","first-page":"1607","article-title":"Approximated oracle filter pruning for destructive CNN width optimization","author":"ding","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref21","first-page":"5113","article-title":"Collaborative channel pruning for deep networks","author":"peng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00290"},{"key":"ref26","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-30484-3_23","article-title":"Simultaneously learning architectures and features of deep neural networks","author":"wang","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00302"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref59","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"hu","year":"2016"},{"key":"ref58","first-page":"1","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Workshop"},{"key":"ref57","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"0","journal-title":"Proc IEEE Symp Oper Syst Des Implement"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref54","article-title":"cuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014"},{"key":"ref53","first-page":"1","article-title":"High performance convolutional neural networks for document processing","author":"chellapilla","year":"0","journal-title":"Proc Int'l Workshop Frontiers in Handwriting Recognition"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00726"},{"key":"ref10","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref40","article-title":"Neural networks with few multiplications","author":"lin","year":"2016"},{"key":"ref12","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","first-page":"6797","article-title":"Auto-balanced filter pruning for efficient convolutional neural networks","author":"ding","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/72.248452"},{"key":"ref15","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref18","first-page":"1","article-title":"Pruning filters for efficient convnets","author":"li","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref19","first-page":"815","article-title":"AMC: AutoML for model compression and acceleration on mobile devices","author":"he","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref4","article-title":"Compact deep convolutional neural networks with coarse pruning","author":"anwar","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref6","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref8","first-page":"1","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"molchanov","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref7","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","first-page":"2852","article-title":"Darkrank: Accelerating deep metric learning via cross sample similarities transfer","author":"chen","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.280"},{"key":"ref46","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref48","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref47","first-page":"1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Workshop"},{"key":"ref42","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","author":"denton","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"525","article-title":"XNOR-Net: ImageNet classification using binary convolutional neural networks","author":"rastegari","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"ref43","article-title":"Speeding-up convolutional neural networks using fine-tuned CP-decomposition","author":"lebedev","year":"2016"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9163420\/08937758.pdf?arnumber=8937758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:08:25Z","timestamp":1651079305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8937758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":72,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2019.2961233","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}