{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T13:57:50Z","timestamp":1783605470008,"version":"3.55.0"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585570","type":"print"},{"value":"9783030585587","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58558-7_29","type":"book-chapter","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T09:03:08Z","timestamp":1603875788000},"page":"491-507","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":545,"title":["Big Transfer (BiT): General Visual Representation Learning"],"prefix":"10.1007","author":[{"given":"Alexander","family":"Kolesnikov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucas","family":"Beyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohua","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joan","family":"Puigcerver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jessica","family":"Yung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sylvain","family":"Gelly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil","family":"Houlsby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"key":"29_CR1","unstructured":"Athiwaratkun, B., Finzi, M., Izmailov, P., Wilson, A.G.: There are many consistent explanations of unlabeled data: why you should average. In: ICLR (2019)"},{"key":"29_CR2","unstructured":"Berthelot, D., et\u00a0al.: ReMixMatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv preprint arXiv:1911.09785 (2019)"},{"key":"29_CR3","unstructured":"Chen, W., Liu, Y., Kira, Z., Wang, Y.F., Huang, J.: A closer look at few-shot classification. In: ICLR (2019)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"29_CR5","unstructured":"De, S., Smith, S.L.: Batch normalization has multiple benefits: an empirical study on residual networks (2020). https:\/\/openreview.net\/forum?id=BJeVklHtPr"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"29_CR7","unstructured":"Goyal, P., et\u00a0al.: Accurate, large minibatch sgd: training imagenet in 1 h. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. arXiv preprint arXiv:1911.05722 (2019)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Girshick, R., Doll\u00e1r, P.: Rethinking imagenet pre-training. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00502"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR11","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"29_CR12","unstructured":"H\u00e9naff, O.J., Razavi, A., Doersch, C., Eslami, S., van den Oord, A.: Data-efficient image recognition with contrastive predictive coding. arXiv preprint arXiv:1905.09272 (2019)"},{"key":"29_CR13","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"29_CR14","unstructured":"Huang, Y., et\u00a0al.: GPipe: Efficient training of giant neural networks using pipeline parallelism. arXiv preprint arXiv:1811.06965 (2018)"},{"key":"29_CR15","unstructured":"Ioffe, S.: Batch renormalization: towards reducing minibatch dependence in batch-normalized models. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 1945\u20131953. Curran Associates, Inc. (2017)"},{"key":"29_CR16","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"29_CR17","unstructured":"Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407 (2018)"},{"key":"29_CR18","doi-asserted-by":"publisher","unstructured":"Joulin, A., van der Maaten, L., Jabri, A., Vasilache, N.: Learning visual features from large weakly supervised data. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 67\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_5","DOI":"10.1007\/978-3-319-46478-7_5"},{"key":"29_CR19","unstructured":"Jouppi, N.P., et\u00a0al.: In-datacenter performance analysis of a tensor processing unit. In: International Symposium on Computer Architecture (ISCA) (2017)"},{"key":"29_CR20","unstructured":"Kaplan, J., et\u00a0al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"29_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"29_CR22","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. University of Toronto, Technical report (2009)"},{"key":"29_CR23","unstructured":"van Laarhoven, T.: L2 regularization versus batch and weight normalization. CoRR (2017)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Li, A., Jabri, A., Joulin, A., van der Maaten, L.: Learning visual n-grams from web data. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.449"},{"key":"29_CR25","unstructured":"Li, X., Grandvalet, Y., Davoine, F.: Explicit inductive bias for transfer learning with convolutional networks. In: ICML (2018)"},{"key":"29_CR26","unstructured":"Li, Z., Arora, S.: An exponential learning rate schedule for deep learning. arXiv preprint arXiv:1910.07454 (2019)"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"29_CR28","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., et\u00a0al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"29_CR29","unstructured":"Loshchilov, I., Hutter, F.: Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"29_CR30","doi-asserted-by":"publisher","unstructured":"Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 185\u2013201. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_12","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"29_CR31","unstructured":"Nakamura, A., Harada, T.: Revisiting fine-tuning for few-shot learning. arXiv preprint arXiv:1910.00216 (2019)"},{"key":"29_CR32","unstructured":"Ngiam, J., Peng, D., Vasudevan, V., Kornblith, S., Le, Q.V., Pang, R.: Domain adaptive transfer learning with specialist models. arXiv:1811.07056 (2018)"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Indian Conference on Computer Vision, Graphics and Image Processing (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng (2009)","DOI":"10.1109\/TKDE.2009.191"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.V.: Cats and dogs. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"29_CR36","unstructured":"Qiao, S., Wang, H., Liu, C., Shen, W., Yuille, A.: Weight standardization. arXiv preprint arXiv:1903.10520 (2019)"},{"key":"29_CR37","unstructured":"Raghu, M., Zhang, C., Kleinberg, J., Bengio, S.: Transfusion: Understanding transfer learning with applications to medical imaging. arXiv:1902.07208 (2019)"},{"key":"29_CR38","unstructured":"Rosenfeld, J.S., Rosenfeld, A., Belinkov, Y., Shavit, N.: A constructive prediction of the generalization error across scales. In: ICLR (2020)"},{"key":"29_CR39","doi-asserted-by":"publisher","unstructured":"Russakovsky, O., et\u00a0al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","DOI":"10.1007\/s11263-015-0816-y"},{"key":"29_CR40","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"29_CR41","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NIPS (2017)"},{"key":"29_CR42","unstructured":"Sohn, K., et\u00a0al.: Fixmatch: Simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685 (2020)"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et\u00a0al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"29_CR46","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"29_CR47","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: ICML (2019)"},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Thomee, B., et\u00a0al.: Yfcc100m: The new data in multimedia research. arXiv preprint arXiv:1503.01817 (2015)","DOI":"10.1145\/2812802"},{"key":"29_CR49","unstructured":"Touvron, H., Vedaldi, A., Douze, M., J\u00e9gou, H.: Fixing the train-test resolution discrepancy. In: NeurIPS (2019)"},{"key":"29_CR50","doi-asserted-by":"crossref","unstructured":"Tschannen, M., et\u00a0al.: Self-supervised learning of video-induced visual invariances. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.01382"},{"key":"29_CR51","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: NIPS (2016)"},{"key":"29_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01261-8_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Wu","year":"2018","unstructured":"Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_1"},{"key":"29_CR53","doi-asserted-by":"crossref","unstructured":"Xie, Q., Hovy, E., Luong, M.T., Le, Q.V.: Self-training with noisy student improves imagenet classification. arXiv preprint arXiv:1911.04252 (2019)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"29_CR54","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"29_CR55","unstructured":"Yalniz, I.Z., J\u00e9gou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546 (2019)"},{"key":"29_CR56","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: Regularization strategy to train strong classifiers with localizable features. arXiv preprint arXiv:1905.04899 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"29_CR57","doi-asserted-by":"crossref","unstructured":"Zhai, X., Oliver, A., Kolesnikov, A., Beyer, L.: S$$^\\mathbf{4}$$L: self-supervised semi-supervised learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00156"},{"key":"29_CR58","unstructured":"Zhai, X., et al.: A large-scale study of representation learning with the visual task adaptation benchmark. arXiv preprint arXiv:1910.04867 (2019)"},{"key":"29_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. In: ICLR (2017)","DOI":"10.1007\/978-1-4899-7687-1_79"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58558-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:55:26Z","timestamp":1730105726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58558-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585570","9783030585587"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58558-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}