{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T21:11:24Z","timestamp":1777497084564,"version":"3.51.4"},"reference-count":140,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721004"],"award-info":[{"award-number":["61721004"]}],"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":["U1803261"],"award-info":[{"award-number":["U1803261"]}],"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":["61976132"],"award-info":[{"award-number":["61976132"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["Z201100006820079"],"award-info":[{"award-number":["Z201100006820079"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research Program of Frontier Sciences CAS","award":["ZDBS-LY-JSC032"],"award-info":[{"award-number":["ZDBS-LY-JSC032"]}]},{"name":"Key Research Program of Frontier Sciences CAS","award":["CAS-AIR"],"award-info":[{"award-number":["CAS-AIR"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/tpami.2022.3153065","type":"journal-article","created":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T20:37:25Z","timestamp":1645648645000},"page":"211-228","source":"Crossref","is-referenced-by-count":48,"title":["Cyclic Differentiable Architecture Search"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4208-1200","authenticated-orcid":false,"given":"Hongyuan","family":"Yu","sequence":"first","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), AI School, University of Chinese Academy of Sciences (UCAS), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8544-8952","authenticated-orcid":false,"given":"Houwen","family":"Peng","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8239-7229","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), AI School, University of Chinese Academy of Sciences (UCAS), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1025-2012","authenticated-orcid":false,"given":"Jianlong","family":"Fu","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), AI School, University of Chinese Academy of Sciences (UCAS), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Ling","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_28"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00378"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref31","article-title":"NAS-bench-201: Extending the scope of reproducible neural architecture search","author":"dong","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref37","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"xie","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref36","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","author":"pham","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00206"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00756"},{"key":"ref29","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref20","first-page":"367","article-title":"Random search and reproducibility for neural architecture search","author":"li","year":"2020","journal-title":"Proc Uncertainty Artif Intell"},{"key":"ref22","article-title":"DARTS+: Improved differentiable architecture search with early stopping","author":"liang","year":"2019"},{"key":"ref21","article-title":"Understanding and robustifying differentiable architecture search","author":"zela","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","article-title":"Evaluating the search phase of neural architecture search","author":"sciuto","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref23","article-title":"Rethinking architecture selection in differentiable NAS","author":"wang","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref101","article-title":"Neural architecture optimization","author":"luo","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref26","article-title":"Weight-sharing neural architecture search: A battle to shrink the optimization gap","author":"xie","year":"2020"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref25","article-title":"Nas evaluation is frustratingly hard","author":"yang","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","article-title":"Joint sub-bands learning with clique structures for wavelet domain super-resolution","volume":"31","author":"zhong","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref59","article-title":"FBNetv3: Joint architecture-recipe search using neural acquisition function","author":"dai","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.154"},{"key":"ref55","article-title":"Designing neural network architectures using reinforcement learning","author":"baker","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref54","first-page":"4053","article-title":"Convolutional neural fabrics","author":"saxena","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2967058"},{"key":"ref52","first-page":"874","article-title":"AdaNet: Adaptive structural learning of artificial neural networks","author":"cortes","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2438548"},{"key":"ref4","first-page":"6642","article-title":"DetNAS: Backbone search for object detection","author":"chen","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00934"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref7","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3099369"},{"key":"ref9","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6955"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2840724"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2716350"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01247-4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6141"},{"key":"ref44","article-title":"Robust subspace segmentation by low-rank representation","author":"liu","year":"2010","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01191"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"ref73","article-title":"Hierarchical representations for efficient architecture search","author":"liu","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_32"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01515-2"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2018.2808689"},{"key":"ref128","article-title":"FasterSeg: Searching for faster real-time semantic segmentation","author":"chen","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205489"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00251"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref74","article-title":"SMASH: One-shot model architecture search through hypernetworks","author":"brock","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref75","first-page":"550","article-title":"Understanding and simplifying one-shot architecture search","author":"bender","year":"2018","journal-title":"Proc IEEE Int Conf Learn Representations"},{"key":"ref133","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref134","article-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"chen","year":"2019"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01289"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054428"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref79","first-page":"12 239","article-title":"FairNAS: Rethinking evaluation fairness of weight sharing neural architecture search","author":"chu","year":"2019","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","article-title":"Once for all: Train one network and specialize it for efficient deployment","author":"cai","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref140","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00257"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref67","first-page":"7105","article-title":"NAS-bench-101: Towards reproducible neural architecture search","author":"ying","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref68","article-title":"NAS-bench-1shot1: Benchmarking and dissecting one-shot neural architecture search","author":"zela","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","first-page":"2905","article-title":"DATA: Differentiable architecture approximation with distribution guided sampling","volume":"43","author":"chang","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2018.8477735"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00215"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054824"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref94","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref107","article-title":"Improved regularization of convolutional neural networks with cutout","author":"devries","year":"2017"},{"key":"ref93","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref106","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref92","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref105","article-title":"FractalNet: Ultra-deep neural networks without residuals","author":"larsson","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref91","article-title":"Evaluating the search phase of neural architecture search","author":"sciuto","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"ref103","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref102","article-title":"Latency-aware differentiable neural architecture search","author":"xu","year":"2020"},{"key":"ref111","article-title":"XNAS: Neural architecture search with expert advice","author":"nayman","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref112","article-title":"ASAP: Architecture search, anneal and prune","author":"noy","year":"2019"},{"key":"ref110","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"},{"key":"ref98","article-title":"A downsampled variant of imagenet as an alternative to the cifar datasets","author":"chrabaszcz","year":"2017"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref96","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref97","first-page":"1437","article-title":"BOHB: Robust and efficient hyperparameter optimization at scale","author":"falkner","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref11","article-title":"Neural architecture search with Bayesian optimisation and optimal transport","author":"kandasamy","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref12","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"elsken","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref13","article-title":"A survey on neural architecture search","author":"wistuba","year":"2019"},{"key":"ref14","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00138"},{"key":"ref118","article-title":"MixConv: Mixed depthwise convolutional kernels","author":"tan","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00660"},{"key":"ref82","article-title":"ISTA-NAS: Efficient and consistent neural architecture search by sparse coding","author":"yang","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01210"},{"key":"ref17","article-title":"SNAS: Stochastic neural architecture search","author":"xie","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref81","article-title":"PC-DARTS: Partial channel connections for memory-efficient architecture search","author":"xu","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00186"},{"key":"ref84","article-title":"Transfer learning with neural automl","author":"wong","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00040"},{"key":"ref19","article-title":"AutoHAS: Efficient hyperparameter and architecture search","author":"dong","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013927"},{"key":"ref114","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"goyal","year":"2017"},{"key":"ref113","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01385"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref89","article-title":"Cream of the crop: Distilling prioritized paths for one-shot neural architecture search","author":"peng","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref121","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref122","article-title":"MixPath: A unified approach for one-shot neural architecture search","author":"chu","year":"2020"},{"key":"ref123","first-page":"552","article-title":"ESPNet: Efficient spatial pyramid of dilated convolutions for semantic segmentation","author":"mehta","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref85","first-page":"247","article-title":"XferNAS: Transfer neural architecture search","author":"wistuba","year":"2020","journal-title":"Proc Eur Conf Mach Learn Knowl Discovery Databases"},{"key":"ref86","article-title":"Efficient neural architecture transformation searchin channel-level for object detection","author":"peng","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3044416"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3052758"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9970415\/09720178.pdf?arnumber=9720178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:12:55Z","timestamp":1672081975000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9720178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":140,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3153065","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":[[2023,1,1]]}}}