{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T14:37:16Z","timestamp":1783089436109,"version":"3.54.6"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Australian Research Council Discovery Program","award":["DP240100181"],"award-info":[{"award-number":["DP240100181"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3529517","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T19:51:08Z","timestamp":1736797868000},"page":"3500-3514","source":"Crossref","is-referenced-by-count":6,"title":["BossNAS Family: Block-Wisely Self-Supervised Neural Architecture Search"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8486-7482","authenticated-orcid":false,"given":"Changlin","family":"Li","sequence":"first","affiliation":[{"name":"Australian Artificial Intelligence Institute, University of Technology Sydney, Broadway, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3235-373X","authenticated-orcid":false,"given":"Sihao","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computing Technologies, RMIT University, Melbourne, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8526-220X","authenticated-orcid":false,"given":"Tao","family":"Tang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7760-1339","authenticated-orcid":false,"given":"Guangrun","family":"Wang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingjie","family":"Li","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, 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":"Future Media Computing Lab, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref3","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref4","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref9","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref11","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref15","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref16","article-title":"TransGAN: Two transformers can make one strong GAN","author":"Jiang","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref19","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph"},{"key":"ref20","first-page":"1","article-title":"Designing neural network architectures using reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baker"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00257"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00492"},{"key":"ref23","article-title":"DeepArchitect: Automatically designing and training deep architectures","author":"Negrinho","year":"2017"},{"key":"ref24","first-page":"1","article-title":"SMASH: One-shot model architecture search through hypernetworks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref25","first-page":"4092","article-title":"Efficient neural architecture search via parameter sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref26","first-page":"549","article-title":"Understanding and simplifying one-shot architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bender"},{"key":"ref27","first-page":"1","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref28","first-page":"1986","article-title":"Blockwisely supervised neural architecture search with knowledge distillation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01385"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01201"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_46"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01076"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01206"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3054824"},{"key":"ref35","article-title":"Stage-wise channel pruning for model compression","author":"Zhang","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107794"},{"key":"ref37","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Komodakis"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref40","article-title":"Understanding deep learning requires rethinking generalization","author":"Zhang","year":"2016"},{"key":"ref41","article-title":"What do neural networks learn when trained with random labels","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Maennel"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_8"},{"key":"ref43","article-title":"Does unsupervised architecture representation learning help neural architecture search","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yan"},{"key":"ref44","article-title":"Self-supervised representation learning for evolutionary neural architecture search","author":"Wei","year":"2020"},{"key":"ref45","article-title":"Contrastive embeddings for neural architectures","author":"Hesslow","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01213"},{"key":"ref47","first-page":"7588","article-title":"Neural architecture search without training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mellor"},{"key":"ref48","first-page":"1","article-title":"Neural architecture search on ImageNet in four GPU hours: A theoretically inspired perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref49","first-page":"1","article-title":"Auto-scaling vision transformers without training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref53","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref54","first-page":"7105","article-title":"NAS-bench-101: Towards reproducible neural architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ying"},{"key":"ref55","first-page":"1","article-title":"NAS-Bench-201: Extending the scope of reproducible neural architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dong"},{"key":"ref56","first-page":"1","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01202"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref61","first-page":"4053","article-title":"Convolutional neural fabrics","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Saxena"},{"key":"ref62","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref64","first-page":"1","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00610"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref71","first-page":"1","article-title":"BEit: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref73","first-page":"1","article-title":"iBOT: Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref74","article-title":"Evaluating the search phase of neural architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sciuto"},{"key":"ref75","first-page":"1","article-title":"NAS evaluation is frustratingly hard","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref76","first-page":"1","article-title":"NAS-bench-1shot1: Benchmarking and dissecting one-shot neural architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zela"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014886"},{"key":"ref79","article-title":"MEAL V2: Boosting vanilla ResNet-50 to 80% top-1 accuracy on ImageNet without tricks","author":"Shen","year":"2020"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref81","first-page":"1","article-title":"Revisiting locally supervised learning: An alternative to end-to-end training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00008"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_9"},{"key":"ref84","article-title":"Transformer in transformer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3194044"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01298"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01433"},{"key":"ref90","first-page":"1","article-title":"Slimmable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3246792"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00850"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10839629.pdf?arnumber=10839629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T18:19:10Z","timestamp":1744654750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10839629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":92,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3529517","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":[[2025,5]]}}}