{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:36:18Z","timestamp":1776278178203,"version":"3.50.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125603"],"award-info":[{"award-number":["62125603"]}],"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":[[2023,9,1]]},"DOI":"10.1109\/tpami.2023.3263824","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:30:35Z","timestamp":1680543035000},"page":"10960-10973","source":"Crossref","is-referenced-by-count":74,"title":["GFNet: Global Filter Networks for Visual Recognition"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3952-8753","authenticated-orcid":false,"given":"Yongming","family":"Rao","sequence":"first","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0920-1576","authenticated-orcid":false,"given":"Wenliang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4435-1692","authenticated-orcid":false,"given":"Zheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref2","volume-title":"Digital Image Processing: Principles and Applications","author":"Baxes","year":"1994"},{"key":"ref3","article-title":"Are we done with ImageNet?","author":"Beyer","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3303397"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref9","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv36zrf8.5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2307\/2003354"},{"key":"ref13","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref14","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","author":"Dao","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref17","first-page":"395","article-title":"CirCNN: Accelerating and compressing deep neural networks using block-circulant weight matrices","volume-title":"Proc. 50th Annu. IEEE\/ACM Int. Symp. Microarchitect.","author":"Ding"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref20","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref21","article-title":"Improve vision transformers training by suppressing over-smoothing","author":"Gong","year":"2021"},{"key":"ref22","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref23","first-page":"1","article-title":"On the connection between local attention and dynamic depth-wise convolution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref30","article-title":"Channel gating neural networks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Hua"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref32","first-page":"667","article-title":"Dynamic filter networks","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref33","article-title":"Token labeling: Training a 85.5% top-1 accuracy vision transformer with 56m parameters on ImageNet","author":"Jiang","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref36","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref37","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00873"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref45","article-title":"Pay attention to MLPs","author":"Liu","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref48","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref49","first-page":"21297","article-title":"SOFT: Softmax-free transformer with linear complexity","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref50","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref51","article-title":"Rethinking the design principles of robust vision transformer","author":"Mao","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref53","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref54","volume-title":"Digital Image Processing Algorithms and Applications","author":"Pitas","year":"2000"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref57","first-page":"980","article-title":"Global filter networks for image classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref58","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref59","article-title":"ImageNet-21k pretraining for the masses","author":"Ridnik","year":"2021"},{"key":"ref60","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref62","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref63","article-title":"MLP-mixer: An all-MLP architecture for vision","author":"Tolstikhin","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3206148"},{"key":"ref65","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref68","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00414"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01055"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref78","article-title":"MorphMLP: A self-attention free, MLP-like backbone for image and video","author":"Zhang","year":"2021"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00681"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10210213\/10091201.pdf?arnumber=10091201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:54:45Z","timestamp":1719345285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10091201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":81,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3263824","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":[[2023,9,1]]}}}