{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T12:47:33Z","timestamp":1793018853644,"version":"4.5.0"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Project for New Generation of AI","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91646207"],"award-info":[{"award-number":["91646207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976208"],"award-info":[{"award-number":["61976208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,9,1]]},"DOI":"10.1109\/tpami.2020.3020300","type":"journal-article","created":{"date-parts":[[2020,8,31]],"date-time":"2020-08-31T21:35:23Z","timestamp":1598909723000},"page":"2891-2904","source":"Crossref","is-referenced-by-count":45,"title":["You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8329-5363","authenticated-orcid":false,"given":"Xinbang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0526-3331","authenticated-orcid":false,"given":"Naiyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2089-9733","authenticated-orcid":false,"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc 18th Int Conf Artif Intell Statist"},{"key":"ref72","article-title":"FractalNet: Ultra-deep neural networks without residuals","author":"larsson","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref71","article-title":"Improved regularization of convolutional neural networks with cutout","author":"devries","year":"2017"},{"key":"ref70","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref77","article-title":"High-resolution representations for labeling pixels and regions","author":"sun","year":"2019"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-007-0002-4"},{"key":"ref75","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2469673"},{"key":"ref30","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/72.265960"},{"key":"ref36","article-title":"Rethinking the value of network pruning","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","first-page":"815","article-title":"AMC: AutoML for model compression and acceleration on mobile devices","author":"he","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref34","article-title":"N2N learning: Network to network compression via policy gradient reinforcement learning","author":"ashok","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref60","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref27","article-title":"Diversity networks","author":"mariet","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref65","article-title":"Hierarchical representations for efficient architecture search","author":"liu","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref66","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015","journal-title":"Proc Int Conf Neural Inf Process Syst Workshop"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858232"},{"key":"ref67","article-title":"Training deep nets with sublinear memory cost","author":"chen","year":"2016"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref69","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref1","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref20","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2748585"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.804317"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2886192"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2874634"},{"key":"ref26","article-title":"Pruning filters for efficient convnets","author":"li","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"hu","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00186"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref59","article-title":"Residual connections encourage iterative inference","author":"jastrzebski","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","first-page":"543","article-title":"A method for solving the convex programming problem with convergence rate $\\varnothing(1\/k^2)$?(1\/k2)","volume":"269","author":"nesterov","year":"0","journal-title":"Dokl Akad Nauk"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1561\/2400000003"},{"key":"ref55","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","author":"ye","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref54","first-page":"122","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","author":"ma","year":"2018","journal-title":"Eur Conf Comput Vis"},{"key":"ref53","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"0"},{"key":"ref52","article-title":"SNAS: Stochastic neural architecture search","author":"xie","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2293418"},{"key":"ref12","first-page":"4092","article-title":"Efficient neural architecture search via parameter sharing","author":"pham","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00257"},{"key":"ref14","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-007-0176-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref81","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref18","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"1993","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","first-page":"1379","article-title":"Dynamic network surgery for efficient DNNs","author":"guo","year":"2016","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref80","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref8","first-page":"2902","article-title":"Large-scale evolution of image classifiers","author":"real","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref49","article-title":"DARTS+: Improved differentiable architecture search with early stopping","author":"liang","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00368"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301216"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2695223"},{"key":"ref41","article-title":"Efficient multi-objective neural architecture search via lamarckian evolution","author":"elsken","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref44","first-page":"549","article-title":"Understanding and simplifying one-shot architecture search","author":"bender","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref43","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9506969\/09181469.pdf?arnumber=9181469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:24Z","timestamp":1652194164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9181469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,1]]},"references-count":81,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3020300","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,1]]}}}