{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T02:45:20Z","timestamp":1790995520165,"version":"4.1.0"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0111601"],"award-info":[{"award-number":["2021ZD0111601"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836012"],"award-info":[{"award-number":["61836012"]}],"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":["62006255"],"award-info":[{"award-number":["62006255"]}],"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":["62325605"],"award-info":[{"award-number":["62325605"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"GuangDong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2023A1515011374"],"award-info":[{"award-number":["2023A1515011374"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100018599","name":"GuangDong Province Key Laboratory of Information Security Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100018599","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3335261","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T19:32:28Z","timestamp":1700595148000},"page":"2722-2740","source":"Crossref","is-referenced-by-count":5,"title":["DNA Family: Boosting Weight-Sharing NAS With Block-Wise Supervisions"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7760-1339","authenticated-orcid":false,"given":"Guangrun","family":"Wang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8486-7482","authenticated-orcid":false,"given":"Changlin","family":"Li","sequence":"additional","affiliation":[{"name":"ReLER lab, AAII, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liuchun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiefeng","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1851-6551","authenticated-orcid":false,"given":"Xiaoyu","family":"Xian","sequence":"additional","affiliation":[{"name":"CRRC Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"ReLER lab, AAII, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref3","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00492"},{"key":"ref5","article-title":"DeepArchitect: Automatically designing and training deep architectures","author":"Negrinho","year":"2017"},{"key":"ref6","first-page":"2020","article-title":"Neural architecture search with Bayesian optimisation and optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kandasamy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17233"},{"key":"ref8","article-title":"Evaluating the search phase of neural architecture search","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Sciuto"},{"key":"ref9","article-title":"{NAS} evaluation is frustratingly hard","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01213"},{"key":"ref11","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref12","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Zoph"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00257"},{"key":"ref14","article-title":"Designing neural network architectures using reinforcement learning","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Baker"},{"key":"ref15","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Cai"},{"key":"ref16","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00186"},{"key":"ref18","article-title":"SMASH: One-shot model architecture search through hypernetworks","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01202"},{"key":"ref22","first-page":"549","article-title":"Understanding and simplifying one-shot architecture search","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Bender"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01385"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007327622663"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00206"},{"key":"ref26","first-page":"2654","article-title":"Do deep nets really need to be deep?","volume-title":"Proc. 27th Annu. Conf. Neural Inf. Process. Syst.","author":"Ba"},{"key":"ref27","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Romero"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/384"},{"key":"ref30","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello"},{"key":"ref31","first-page":"3351","article-title":"Self-distillation amplifies regularization in hilbert space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mobahi"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_46"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01076"},{"key":"ref35","first-page":"12486","article-title":"Does unsupervised architecture representation learning help neural architecture search?","volume-title":"Proc. 33th Annu. Conf. Neural Inf. Process. Syst.","author":"Yan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070605"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01206"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00008"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"ref42","article-title":"NASViT: Neural architecture search for efficient vision transformers with gradient conflict aware supernet training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gong"},{"key":"ref43","first-page":"8714","article-title":"Searching the search space of vision transformer","volume":"34","author":"Chen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref44","article-title":"Efficient neural architecture search via parameter sharing","author":"Pham","year":"2018"},{"key":"ref45","first-page":"279","article-title":"Modular learning in neural networks","volume-title":"Proc. 6th Nat. Conf. Artif. Intell.","author":"Ballard"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.123"},{"key":"ref49","article-title":"SCARLETNAS: Bridging the gap between scalability and fairness in neural architecture search","author":"Chu","year":"2019"},{"key":"ref50","article-title":"Computation reallocation for object detection","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Liang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00937"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00944"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref56","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","author":"Bardes","year":"2021"},{"key":"ref57","first-page":"12 310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref59","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref64","article-title":"Moga: Searching beyond MobileNetV3","author":"Chu","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref66","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref67","article-title":"Slimmable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00850"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3246792"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3194044"},{"key":"ref71","article-title":"RandAugment: Practical data augmentation with no separate search","author":"Cubuk","year":"2019"},{"key":"ref72","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00140","article-title":"Searching for MobileNetV3","author":"Howard","year":"2019"},{"key":"ref73","article-title":"MixConv: Mixed depthwise convolutional kernels","author":"Tan","year":"2019"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01601"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00635"},{"key":"ref76","first-page":"10 760","article-title":"AlphaNet: Improved training of supernets with alpha-divergence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref77","first-page":"10 096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref78","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","author":"Cai","year":"2019"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref80","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref81","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref84","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref90","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref91","article-title":"Understanding and robustifying differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Arber Zela"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref96","article-title":"FBNetV5: Neural architecture search for multiple tasks in one run","author":"Wu","year":"2021"},{"key":"ref97","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref98","article-title":"PERF: Panoramic neural radiance field from a single panorama","author":"Wang","year":"2023"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00832"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321857"},{"key":"ref101","article-title":"Traditional classification neural networks are good generators: They are competitive with DDPMs and GANs","author":"Wang","year":"2022"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_28"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555447"},{"key":"ref104","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10324326.pdf?arnumber=10324326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:34:06Z","timestamp":1712691246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10324326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":104,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3335261","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":[[2024,5]]}}}