{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:44:58Z","timestamp":1732041898725,"version":"3.28.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"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":[[2022,6]]},"DOI":"10.1109\/cvpr52688.2022.01179","type":"proceedings-article","created":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T15:56:41Z","timestamp":1664294201000},"page":"1204-1213","source":"Crossref","is-referenced-by-count":360,"title":["Scaling Vision Transformers"],"prefix":"10.1109","author":[{"given":"Xiaohua","family":"Zhai","sequence":"first","affiliation":[{"name":"Google Research, Brain Team,Zurich"}]},{"given":"Alexander","family":"Kolesnikov","sequence":"additional","affiliation":[{"name":"Google Research, Brain Team,Zurich"}]},{"given":"Neil","family":"Houlsby","sequence":"additional","affiliation":[{"name":"Google Research, Brain Team,Zurich"}]},{"given":"Lucas","family":"Beyer","sequence":"additional","affiliation":[{"name":"Google Research, Brain Team,Zurich"}]}],"member":"263","reference":[{"key":"ref39","first-page":"10118","article-title":"1-bit adam: Communication efficient large-scale training with adam's convergence speed","volume":"139","author":"tang","year":"0","journal-title":"Proceedings of the 38th International Conference on Machine Learning ICML 2021"},{"key":"ref38","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","volume":"139","author":"tan","year":"0","journal-title":"Proceedings of the 38th International Conference on Machine Learning ICML 2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref32","article-title":"Do imagenet classifiers generalize to imagenet?","author":"recht","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref30","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref37","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"0","journal-title":"ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref34","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","author":"shazeer","year":"0","journal-title":"ICML"},{"key":"ref28","article-title":"Meta pseudo labels","author":"pham","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref2","article-title":"Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","author":"barbu","year":"0","journal-title":"NeurIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462557"},{"key":"ref20","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"jia","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Big Transfer (BiT): General Visual Representation Learning","author":"kolesnikov","year":"0","journal-title":"ECCV"},{"key":"ref21","article-title":"Scaling laws for neural language models","author":"kaplan","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","author":"lee","year":"0","journal-title":"ICML"},{"key":"ref23","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Technical Report"},{"key":"ref26","article-title":"Exploring the limits of weakly supervised pretraining","author":"mahajan","year":"0","journal-title":"ECCV"},{"key":"ref25","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","author":"lepikhin","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref51","first-page":"1476","article-title":"S41: Self-supervised semi-supervised learning","author":"zhai","year":"0","journal-title":"ICCV"},{"key":"ref53","article-title":"Deepvit: Towards deeper vision transformer","author":"zhou","year":"2021","journal-title":"CoRR abs\/2103 11886"},{"key":"ref52","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","author":"zhai","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"On the relationship between self-attention and convolutional layers","author":"cordonnier","year":"0","journal-title":"ICLRE"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref40","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Coatnet: Marrying convolution and attention for all data sizes","author":"dai","year":"2021","journal-title":"CoRR abs\/2106 04803"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale","author":"dosovitskiy","year":"0","journal-title":"ICLRE"},{"key":"ref16","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"Scaling laws for autoregressive generative modeling","author":"henighan","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","author":"huang","year":"0","journal-title":"NeurIPS"},{"key":"ref4","article-title":"Are we done with imagenet","author":"beyer","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Revisiting resnets: Improved training and scaling strategies","author":"bello","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"brown","year":"0","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref9","article-title":"Big self-supervised models are strong semi-supervised learners","author":"chen","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref46","article-title":"Caltech-UCSD Birds 200","author":"welinder","year":"2010","journal-title":"Technical Report CNS-TR-2010–001 California Institute of Technology"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref48","article-title":"Self-training with noisy student improves imagenet classification","author":"xie","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref47","article-title":"Resnet strikes back: An improved training procedure in timm","author":"wightman","year":"2021","journal-title":"CoRR abs\/2110 00476"},{"key":"ref42","article-title":"Fixing the train-test resolution discrepancy","author":"touvron","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref44","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"}],"event":{"name":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2022,6,18]]},"location":"New Orleans, LA, USA","end":{"date-parts":[[2022,6,24]]}},"container-title":["2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9878378\/9878366\/09880094.pdf?arnumber=9880094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T16:56:06Z","timestamp":1665766566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9880094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/cvpr52688.2022.01179","relation":{},"subject":[],"published":{"date-parts":[[2022,6]]}}}