{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T21:05:01Z","timestamp":1783976701099,"version":"3.55.0"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"New Generation Artificial Intelligence-National Science and Technology Major Projection","award":["2025ZD0123100"],"award-info":[{"award-number":["2025ZD0123100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573399"],"award-info":[{"award-number":["62573399"]}],"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":["U25A20530"],"award-info":[{"award-number":["U25A20530"]}],"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":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3673336","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:36:39Z","timestamp":1773347799000},"page":"8798-8812","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Training of Large Vision Models via Advanced Automated Progressive Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8486-7482","authenticated-orcid":false,"given":"Changlin","family":"Li","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"North China Electric Power University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3235-373X","authenticated-orcid":false,"given":"Sihao","family":"Lin","sequence":"additional","affiliation":[{"name":"Responsible AI Research Centre, Adelaide University, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8783-8313","authenticated-orcid":false,"given":"Zongxin","family":"Yang","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2219-5569","authenticated-orcid":false,"given":"Junwei","family":"Liang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 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, 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":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref2","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref4","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","first-page":"3965","article-title":"CoatNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1787"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref15","article-title":"Carbon emissions and large neural network training","author":"Patterson","year":"2021"},{"key":"ref16","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frankle","year":"2019"},{"key":"ref17","article-title":"Efficientnetv2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2021"},{"key":"ref18","first-page":"2337","article-title":"Efficient training of bert by progressively stacking","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gong","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.515"},{"key":"ref21","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karras","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.306"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.151"},{"key":"ref24","article-title":"Learning to grow pretrained models for efficient transformer training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0144"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00538"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401036"},{"key":"ref28","article-title":"Budgeted training for vision transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pan","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref32","article-title":"Auto seg-loss: Searching metric surrogates for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00206"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3335261"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01202"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00040"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.405"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3395423"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00390"},{"key":"ref43","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref44","first-page":"32100","article-title":"Dora: Weight-decomposed low-rank adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01524"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref48","article-title":"Progressively stacking 2.0: A multi-stage layerwise training method for bert training speedup","author":"Yang","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.406"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2014"},{"key":"ref51","article-title":"Multi-level residual networks from dynamical systems view","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chang","year":"2018"},{"key":"ref52","first-page":"2616","article-title":"Towards adaptive residual network training: A neural-ode perspective","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dong","year":"2020"},{"key":"ref53","article-title":"Net2net: Accelerating learning via knowledge transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2016"},{"key":"ref54","first-page":"564","article-title":"Network morphism","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei","year":"2016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref56","first-page":"3875","article-title":"Bootstrap latent-predictive representations for multitask reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref58","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Laine","year":"2017"},{"key":"ref59","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tarvainen","year":"2017"},{"key":"ref60","first-page":"161","article-title":"Multi-objective optimization","volume-title":"Decision Sciences","author":"Deb, S. Karthik, and H. Jussi.","year":"2016"},{"key":"ref61","first-page":"6105","article-title":"Efficientnet:Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref64","article-title":"Autoslim: Towards one-shot architecture search for channel numbers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop","author":"Yu","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01206"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref68","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Evci","year":"2020"},{"key":"ref69","first-page":"6377","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tanaka","year":"2020"},{"key":"ref70","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2019"},{"key":"ref71","article-title":"Proxylessnas: Direct neural architecture search on target task and hardware","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai","year":"2019"},{"key":"ref72","first-page":"580","article-title":"Dada: Differentiable automatic data augmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Li","year":"2020"},{"key":"ref73","article-title":"Neural architecture search on imagenet in four GPU hours: A theoretically inspired perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref74","first-page":"10462","article-title":"Disentangling trainability and generalization in deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao","year":"2020"},{"key":"ref75","first-page":"8580","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jacot","year":"2018"},{"key":"ref76","first-page":"8572","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2019"},{"key":"ref77","article-title":"Zico: Zero-shot NAS via inverse coefficient of variation on gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2023"},{"key":"ref78","article-title":"The large learning rate phase of deep learning: The catapult mechanism","author":"Lewkowycz","year":"2020"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref80","article-title":"The artbench dataset: Benchmarking generative models with artworks","author":"Liao","year":"2022"},{"key":"ref81","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11433112.pdf?arnumber=11433112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:04:14Z","timestamp":1783973054000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":87,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3673336","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":[[2026,8]]}}}