{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:23:02Z","timestamp":1783610582919,"version":"3.55.0"},"reference-count":102,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["62202014"],"award-info":[{"award-number":["62202014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Basic Research Program","award":["JCYJ20220813151736001"],"award-info":[{"award-number":["JCYJ20220813151736001"]}]},{"name":"CCF Tencent Open Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3206108","type":"journal-article","created":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T19:55:24Z","timestamp":1663012524000},"page":"1-13","source":"Crossref","is-referenced-by-count":164,"title":["VOLO: Vision Outlooker for Visual Recognition"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2120-5588","authenticated-orcid":false,"given":"Li","family":"Yuan","sequence":"first","affiliation":[{"name":"Peking University, School of Electronic and Computer Engineering, Shenzhen Graduate School, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8388-8708","authenticated-orcid":false,"given":"Qibin","family":"Hou","sequence":"additional","affiliation":[{"name":"TMCC, School of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8096-842X","authenticated-orcid":false,"given":"Zihang","family":"Jiang","sequence":"additional","affiliation":[{"name":"ECE, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-0064","authenticated-orcid":false,"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"Sea AI Lab., Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Sea AI Lab., Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref2","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00064"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref8","first-page":"1059","article-title":"High-performance large-scale image recognition without normalization","author":"Brock","year":"2021","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref9","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref10","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2014","journal-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Deep Learn. Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","first-page":"18590","article-title":"All tokens matter: Token labeling for training better vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref15","article-title":"Drawing multiple augmentation samples per image during training efficiently decreases test error","author":"Fort","year":"2021"},{"key":"ref16","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref17","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref23","first-page":"4467","article-title":"Dual path networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref24","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref26","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref27","article-title":"Fixing the train-test resolution discrepancy","volume":"32","author":"Touvron","year":"2019","journal-title":"Proc. Adv. Neural Inform. Process. Syst."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref32","first-page":"9401","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref35","first-page":"352","article-title":"A$^{2}$2-nets: Double attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref37","article-title":"Stand-alone self-attention in vision models","volume":"32","author":"Ramachandran","year":"2019","journal-title":"Proc. Adv. Neural Inform. Process. Syst."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416301"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416300"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref45","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref46","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Proc. Adv. Neural Inform. Process. Syst."},{"key":"ref47","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1005"},{"key":"ref49","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref50","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref52","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"Proc. Adv. Neural Inform. Process. Syst."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref55","article-title":"Refiner: Refining self-attention for vision transformers","author":"Zhou","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref59","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref61","article-title":"Improve vision transformers training by suppressing over-smoothing","author":"Gong","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref63","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref67","article-title":"Pay less attention with lightweight and dynamic convolutions","author":"Wu","year":"2018","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref70","first-page":"10096","article-title":"EfficientNetv2: Smaller models and faster training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref73","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref74","article-title":"Pytorch image models","author":"Wightman","year":"2019"},{"key":"ref75","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2018","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref76","article-title":"mixup: Beyond empirical risk minimization","author":"Zhang","year":"2018","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref77","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref79","article-title":"Are we done with imagenet?","author":"Beyer","year":"2020"},{"key":"ref80","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3145427"},{"key":"ref82","first-page":"30008","article-title":"Focal attention for local-global interactions in vision transformers","volume":"34","author":"Yang","year":"2021","journal-title":"Proc. Adv. Neural Inform. Process. Syst."},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref85","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","volume":"34","author":"Ali","year":"2021","journal-title":"Proc. Advances Neural Inform. Process. Syst."},{"key":"ref86","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref87","article-title":"MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref95","first-page":"8699","article-title":"Searching for efficient multi-scale architectures for dense image prediction","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref99","article-title":"Dilated SpineNet for semantic segmentation","author":"Rashwan","year":"2021"},{"key":"ref100","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Proc. Adv. Neural Inform. Process. Syst."},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09888055.pdf?arnumber=9888055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:14:51Z","timestamp":1705958091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9888055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3206108","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":[[2022]]}}}