{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:46Z","timestamp":1740169366946,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government [Ministry of Science and ICT (MSIT)]","doi-asserted-by":"publisher","award":["2021-0-00766"],"award-info":[{"award-number":["2021-0-00766"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3350732","type":"journal-article","created":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T19:57:22Z","timestamp":1704743842000},"page":"10242-10253","source":"Crossref","is-referenced-by-count":1,"title":["Method for Expanding Search Space With Hybrid Operations in DynamicNAS"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0233-9638","authenticated-orcid":false,"given":"Iksoo","family":"Shin","sequence":"first","affiliation":[{"name":"Artificial Intelligence Research Laboratory, Future Computing Research Division, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}]},{"given":"Changsik","family":"Cho","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Laboratory, Future Computing Research Division, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4300-7667","authenticated-orcid":false,"given":"Seon-Tae","family":"Kim","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Laboratory, Future Computing Research Division, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref3","first-page":"5598","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2023.128771"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref7","article-title":"DARTS: Differentiable architecture search","author":"Liu","year":"2018","journal-title":"arXiv:1806.09055"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref10","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3212767"},{"key":"ref14","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","author":"Cai","year":"2019","journal-title":"arXiv:1908.09791"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00635"},{"article-title":"NASViT: Neural architecture search for efficient vision transformers with gradient conflict aware supernet training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gong","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3473330"},{"key":"ref19","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_28"},{"key":"ref21","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"Cai","year":"2018","journal-title":"arXiv:1812.00332"},{"key":"ref22","article-title":"Slimmable neural networks","author":"Yu","year":"2018","journal-title":"arXiv:1812.08928"},{"key":"ref23","article-title":"FocusFormer: Focusing on what we need via architecture sampler","author":"Liu","year":"2022","journal-title":"arXiv:2208.10861"},{"key":"ref24","article-title":"PreNAS: Preferred one-shot learning towards efficient neural architecture search","author":"Wang","year":"2023","journal-title":"arXiv:2304.14636"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_39"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref27","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ioffe"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref29","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"ref31","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Han"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"ref33","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xiao"},{"key":"ref34","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","volume":"34","author":"Tolstikhin"},{"key":"ref35","first-page":"8714","article-title":"Searching the search space of vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref36","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016","journal-title":"arXiv:1611.01578"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref38","first-page":"10760","article-title":"AlphaNet: Improved training of supernets with alpha-divergence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10382520.pdf?arnumber=10382520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T02:18:51Z","timestamp":1706753931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10382520\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3350732","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}