{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T11:44:25Z","timestamp":1782906265333,"version":"3.54.5"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science and Technology","award":["2022ZD0118202"],"award-info":[{"award-number":["2022ZD0118202"]}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037"],"award-info":[{"award-number":["U21B2037"]}],"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":["U22B2051"],"award-info":[{"award-number":["U22B2051"]}],"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":["62176222"],"award-info":[{"award-number":["62176222"]}],"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":["62176223"],"award-info":[{"award-number":["62176223"]}],"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":["62176226"],"award-info":[{"award-number":["62176226"]}],"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":["62072386"],"award-info":[{"award-number":["62072386"]}],"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":["62072387"],"award-info":[{"award-number":["62072387"]}],"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":["62072389"],"award-info":[{"award-number":["62072389"]}],"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":["62002305"],"award-info":[{"award-number":["62002305"]}],"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":["62272401"],"award-info":[{"award-number":["62272401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2021J01002"],"award-info":[{"award-number":["2021J01002"]}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2022J06001"],"award-info":[{"award-number":["2022J06001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tpami.2024.3378781","type":"journal-article","created":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T18:22:51Z","timestamp":1710872571000},"page":"6525-6541","source":"Crossref","is-referenced-by-count":12,"title":["Training-Free Transformer Architecture Search With Zero-Cost Proxy Guided Evolution"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3941-3534","authenticated-orcid":false,"given":"Qinqin","family":"Zhou","sequence":"first","affiliation":[{"name":"Media Analytics and Computing Lab, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-3241","authenticated-orcid":false,"given":"Kekai","family":"Sheng","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Science, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6855-5403","authenticated-orcid":false,"given":"Xiawu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Media Analytics and Computing Lab, School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7998-0731","authenticated-orcid":false,"given":"Ke","family":"Li","sequence":"additional","affiliation":[{"name":"YouTu Laboratory, Tencent Company, Ltd., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9765-4523","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref7","article-title":"ISTR: End-to-end instance segmentation with transformers","author":"Hu","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref9","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref11","first-page":"5877","article-title":"The evolved transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"So"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00488"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00378"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3065138"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069250"},{"key":"ref19","first-page":"8714","article-title":"Searching the search space of vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref20","first-page":"1","article-title":"Darts: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref21","first-page":"1","article-title":"Picking winning tickets before training by preserving gradient flow","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref22","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":"ref23","first-page":"7588","article-title":"Neural architecture search without training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mellor"},{"key":"ref24","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref25","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_9"},{"key":"ref28","first-page":"1","article-title":"NASI: Label-and data-agnostic neural architecture search at initialization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shu"},{"key":"ref29","first-page":"1","article-title":"Gradsign: Model performance inference with theoretical insights","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref30","first-page":"1613","article-title":"Knas: Green neural architecture search","author":"Xu","year":"2021","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01062"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref33","article-title":"OVO: One-shot vision transformer search with online distillation","author":"Wei","year":"2022"},{"key":"ref34","article-title":"Searching for efficient multi-stage vision transformers","author":"Liao","year":"2021"},{"key":"ref35","first-page":"1","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":"ref36","first-page":"24254","article-title":"LiteTransformerSearch: Training-free neural architecture search for efficient language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Javaheripi"},{"key":"ref37","first-page":"1","article-title":"Zero-cost proxies for lightweight NAS","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Abdelfattah"},{"key":"ref38","first-page":"1","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00040"},{"key":"ref40","first-page":"33001","article-title":"Unifying and boosting gradient-based training-free neural architecture search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01785-y"},{"key":"ref42","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":"ref43","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref44","first-page":"2793","article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dong"},{"key":"ref45","article-title":"Matrix rank minimization with applications","author":"Fazel","year":"2002"},{"key":"ref46","first-page":"6377","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tanaka"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/72.248452"},{"key":"ref48","first-page":"17629","article-title":"Pruning filter in filter","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Meng"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.529"},{"key":"ref50","first-page":"14014","article-title":"Are sixteen heads really better than one?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Michel"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref52","first-page":"1","article-title":"Drawing early-bird tickets: Towards more efficient training of deep networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"You"},{"key":"ref53","first-page":"1","article-title":"A signal propagation perspective for pruning neural networks at initialization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref58","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref60","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref63","article-title":"Improving language understanding with unsupervised learning","author":"Radford","year":"2018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref65","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ali"},{"key":"ref66","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref67","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xizhou"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref69","article-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref71","first-page":"2596","article-title":"Complexity of linear regions in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hanin"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10666888\/10475573.pdf?arnumber=10475573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:51:43Z","timestamp":1725684703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10475573\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":71,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3378781","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":[[2024,10]]}}}