{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T01:30:46Z","timestamp":1779931846286,"version":"3.53.1"},"reference-count":72,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0105200"],"award-info":[{"award-number":["2020AAA0105200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence"},{"name":"Sponsorship of the Research Grants Council of Hong Kong"},{"name":"Hong Kong General Research Fund","award":["16203319"],"award-info":[{"award-number":["16203319"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China\/the Research Grants Council Joint Research Scheme through the Research Grants Council (RGC) Research Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3112041","type":"journal-article","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T20:09:58Z","timestamp":1632254998000},"page":"8034-8045","source":"Crossref","is-referenced-by-count":21,"title":["Joint Multi-Dimension Pruning via Numerical Gradient Update"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5856-2506","authenticated-orcid":false,"given":"Zechun","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4560-5092","authenticated-orcid":false,"given":"Zhiqiang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3885-4912","authenticated-orcid":false,"given":"Kwang-Ting","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref71","first-page":"875","article-title":"Discrimination-aware channel pruning for deep neural networks","author":"zhuang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref70","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3088904","article-title":"Effective training of convolutional neural networks with low-bitwidth weights and activations","author":"zhuang","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref39","article-title":"Rethinking the value of network pruning","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref33","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref32","first-page":"6438","article-title":"Towards compact CNNs via collaborative compression","author":"li","year":"2021","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref31","article-title":"Pruning filters for efficient convnets","author":"li","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref30","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref36","article-title":"Darts: Differentiable architecture search","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00290"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/336"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref62","article-title":"SNAS: Stochastic neural architecture search","author":"xie","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00137"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"ref28","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"hu","year":"2016","journal-title":"arXiv 1607 03250"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553522"},{"key":"ref27","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref65","article-title":"Slimmable neural networks","author":"yu","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00340"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00156"},{"key":"ref2","first-page":"549","article-title":"Understanding and simplifying one-shot architecture search","author":"bender","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","article-title":"A survey of evolution strategies","volume":"2","author":"back","year":"1991","journal-title":"Proc 4th Int Conf Genetic Algorithms"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref25","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref51","first-page":"3839","article-title":"Lipschitz regularity of deep neural networks: Analysis and efficient estimation","author":"scaman","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref59","article-title":"Efficient deep neural networks","author":"wu","year":"2019","journal-title":"arXiv 1908 08926"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref57","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref55","article-title":"Single-path NAS: Designing hardware-efficient ConvNets in less than 4 hours","author":"stamoulis","year":"2019","journal-title":"arXiv 1904 02877"},{"key":"ref54","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","article-title":"MEAL v2: Boosting vanilla ResNet-50 to 80%+ top-1 accuracy on ImageNet without tricks","author":"shen","year":"2020","journal-title":"arXiv 2009 08453"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00508"},{"key":"ref11","first-page":"11427","article-title":"Efficient and accurate estimation of Lipschitz constants for deep neural networks","volume":"32","author":"fazlyab","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107461"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05929-w"},{"key":"ref14","first-page":"3846","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","author":"gu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"1379","article-title":"Dynamic network surgery for efficient dnns","author":"guo","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"544","article-title":"Single path one-shot neural architecture search with uniform sampling","author":"guo","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref4","first-page":"1","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","author":"cai","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015059928466"},{"key":"ref6","first-page":"14747","article-title":"Storage efficient and dynamic flexible runtime channel pruning via deep reinforcement learning","volume":"33","author":"chen","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"1","article-title":"Proxylessnas: Direct neural architecture search on target task and hardware","author":"cai","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref8","article-title":"A closer look at structured pruning for neural network compression","author":"crowley","year":"2018","journal-title":"arXiv 1810 04622"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00353"},{"key":"ref49","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv 1703 03864"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01166"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref45","article-title":"Combining policy gradient and Q-learning","author":"o\u2019donoghue","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref47","author":"rechenberg","year":"1994","journal-title":"Evolutions Strategies"},{"key":"ref42","first-page":"116","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","author":"ma","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09542852.pdf?arnumber=9542852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T21:49:13Z","timestamp":1673300953000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9542852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3112041","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}