{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T11:08:05Z","timestamp":1750763285229,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,9]]},"DOI":"10.1109\/icast57874.2023.10359276","type":"proceedings-article","created":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T19:23:24Z","timestamp":1703186604000},"page":"129-135","source":"Crossref","is-referenced-by-count":1,"title":["Compact Convolutional Transformer based on Sharpness-Aware Minimization for Image Classification"],"prefix":"10.1109","author":[{"given":"Li-Hua","family":"Li","sequence":"first","affiliation":[{"name":"Chaoyang University of Technology,Department of Information Management,Taichung,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radius","family":"Tanone","sequence":"additional","affiliation":[{"name":"Chaoyang University of Technology,Department of Information Management,Taichung,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3234150"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100379"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105151"},{"article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","volume-title":"3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc","author":"Simonyan","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"author":"Howard","key":"ref9","article-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications"},{"issue":"Nips","key":"ref10","first-page":"1","article-title":"Attention Is All You Need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"author":"Dosovitskiy","key":"ref11","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale"},{"article-title":"Escaping the Big Data Paradigm with Compact Transformers","year":"2021","author":"Hassani","key":"ref12"},{"article-title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","year":"2020","author":"Foret","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_37"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3247877"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27499-2_43"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1025746"},{"key":"ref18","first-page":"639","article-title":"Towards Understanding Sharpness-Aware Minimization","volume-title":"Proc. Mach. Learn. Res","volume":"162","author":"Andriushchenko"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/ppa.13661"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120234"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-022-02064-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-32041-5_12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.32604\/iasc.2023.030017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app122110966"},{"author":"Chen","key":"ref25","article-title":"When Vision Transformers Outperform Resnets Without Pre-Training or Strong Data Augmentations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.508"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/s0893-6080(98)00116-6"},{"article-title":"Adam: A Method for Stochastic Optimization","volume-title":"3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc","author":"Kingma","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15832\/ankutbd.862482"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15316\/sjafs.2021.252"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18201\/ijisae.2019355381"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2021.106285"},{"article-title":"ADADELTA: An Adaptive Learning Rate Method","year":"2012","author":"Zeiler","key":"ref34"},{"volume-title":"RMSProp Explained | Papers With Code","key":"ref35"}],"event":{"name":"2023 12th International Conference on Awareness Science and Technology (iCAST)","start":{"date-parts":[[2023,11,9]]},"location":"Taichung, Taiwan","end":{"date-parts":[[2023,11,11]]}},"container-title":["2023 12th International Conference on Awareness Science and Technology (iCAST)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10359246\/10359247\/10359276.pdf?arnumber=10359276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T21:41:57Z","timestamp":1705095717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10359276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icast57874.2023.10359276","relation":{},"subject":[],"published":{"date-parts":[[2023,11,9]]}}}