{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T11:43:05Z","timestamp":1774611785169,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"the Challengeable Future Defense Technology Research and Development Program through the Agency For Defense Development(ADD) funded by the Defense Acquisition Program Administration (DAPA) in 2022","award":["915034201"],"award-info":[{"award-number":["915034201"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3316144","type":"journal-article","created":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T18:05:59Z","timestamp":1695060359000},"page":"102430-102443","source":"Crossref","is-referenced-by-count":3,"title":["Discrete Wavelet Transform Meets Transformer: Unleashing the Full Potential of the Transformer for Visual Recognition"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3899-2987","authenticated-orcid":false,"given":"Dongwook","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4890-8563","authenticated-orcid":false,"given":"Seung-Woo","family":"Seo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref57","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"2017","journal-title":"arXiv 1710 09412"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref15","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00889-8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218735"},{"key":"ref52","first-page":"2172","article-title":"AFF-CAM: Adaptive frequency filtering based channel attention module","author":"yang","year":"2022","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref11","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref10","first-page":"2286","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","author":"d\u2019ascoli","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref18","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","author":"katharopoulos","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref48","article-title":"ResNet strikes back: An improved training procedure in timm","author":"wightman","year":"2021","journal-title":"arXiv 2110 00476"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref42","article-title":"Patches are all you need?","author":"trockman","year":"2022","journal-title":"arXiv 2201 09792"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref44","article-title":"Linformer: Self-attention with linear complexity","author":"wang","year":"2020","journal-title":"arXiv 2006 04768"},{"key":"ref43","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053878"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref9","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref4","year":"2020","journal-title":"MMSegmentation Openmmlab semantic segmentation toolbox and benchmark"},{"key":"ref3","article-title":"Rethinking attention with performers","author":"choromanski","year":"2020","journal-title":"arXiv 2009 14794"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref5","article-title":"Uses of complex wavelets in deep convolutional neural networks","author":"cotter","year":"2020"},{"key":"ref40","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref37","article-title":"Sequencer: Deep LSTM for image classification","author":"tatsunami","year":"2022","journal-title":"arXiv 2205 01972"},{"key":"ref36","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","author":"tan","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref30","first-page":"980","article-title":"Global filter networks for image classification","volume":"34","author":"rao","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref1","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"chen","year":"2019","journal-title":"ArXiv 1906 07155"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"5314","DOI":"10.1109\/TPAMI.2022.3206148","article-title":"ResMLP: Feedforward networks for image classification with data-efficient training","volume":"45","author":"touvron","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref38","first-page":"24261","article-title":"MLP-Mixer: An all-MLP architecture for vision","volume":"34","author":"tolstikhin","year":"2021","journal-title":"Proc 35th Conf Neural Inf Process Syst"},{"key":"ref24","article-title":"EfficientFormer: Vision transformers at MobileNet speed","author":"li","year":"2022","journal-title":"arXiv 2206 01191"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00543"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref20","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00727"},{"key":"ref21","article-title":"FNet: Mixing tokens with Fourier transforms","author":"lee-thorp","year":"2021","journal-title":"arXiv 2105 03824"},{"key":"ref28","first-page":"1","article-title":"When does label smoothing help?","volume":"32","author":"m\u00fcller","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/T-AIEE.1928.5055024"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10254205.pdf?arnumber=10254205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:59:14Z","timestamp":1730105954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10254205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3316144","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}