{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:21:00Z","timestamp":1774599660838,"version":"3.50.1"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198205","type":"print"},{"value":"9783031198212","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19821-2_26","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"456-473","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":166,"title":["Masked Siamese Networks for\u00a0Label-Efficient Learning"],"prefix":"10.1007","author":[{"given":"Mahmoud","family":"Assran","sequence":"first","affiliation":[]},{"given":"Mathilde","family":"Caron","sequence":"additional","affiliation":[]},{"given":"Ishan","family":"Misra","sequence":"additional","affiliation":[]},{"given":"Piotr","family":"Bojanowski","sequence":"additional","affiliation":[]},{"given":"Florian","family":"Bordes","sequence":"additional","affiliation":[]},{"given":"Pascal","family":"Vincent","sequence":"additional","affiliation":[]},{"given":"Armand","family":"Joulin","sequence":"additional","affiliation":[]},{"given":"Mike","family":"Rabbat","sequence":"additional","affiliation":[]},{"given":"Nicolas","family":"Ballas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Semi-supervised learning of visual features by non-parametrically predicting view assignments with support samples. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00833"},{"key":"26_CR2","unstructured":"Atito, S., Awais, M., Kittler, J.: SiT: self-supervised vision transformer. arXiv preprint arXiv:2104.03602 (2021)"},{"key":"26_CR3","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. arXiv preprint arXiv:2202.03555 (2022)"},{"key":"26_CR4","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"26_CR5","unstructured":"Bao, H., Dong, L., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"26_CR6","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VICReg: variance-invariance-covariance regularization for self-supervised learning. arXiv preprint arXiv:2105.04906 (2021)"},{"issue":"6356","key":"26_CR7","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1038\/355161a0","volume":"355","author":"S Becker","year":"1992","unstructured":"Becker, S., Hinton, G.E.: Self-organizing neural network that discovers surfaces in random-dot stereograms. Nature 355(6356), 161\u2013163 (1992)","journal-title":"Nature"},{"key":"26_CR8","unstructured":"Bordes, F., Balestriero, R., Vincent, P.: High fidelity visualization of what your self-supervised representation knows about. arXiv preprint arXiv:2112.09164 (2021)"},{"issue":"04","key":"26_CR9","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1142\/S0218001493000339","volume":"7","author":"J Bromley","year":"1993","unstructured":"Bromley, J., et al.: Signature verification using a \u201cSiamese\u2019\u2019 time delay neural network. Int. J. Pattern Recognit Artif Intell. 7(04), 669\u2013688 (1993)","journal-title":"Int. J. Pattern Recognit Artif Intell."},{"key":"26_CR10","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"26_CR12","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020)"},{"key":"26_CR13","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. preprint arXiv:2002.05709 (2020)"},{"key":"26_CR14","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.: Big self-supervised models are strong semi-supervised learners. arXiv preprint arXiv:2006.10029 (2020)"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. arXiv preprint arXiv:2011.10566 (2020)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. arXiv preprint arXiv:2104.02057 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation strategies from data. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"26_CR18","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1422\u20131430 (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"26_CR20","unstructured":"Donahue, J., Simonyan, K.: Large scale adversarial representation learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"26_CR21","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Springenberg, J.T., Riedmiller, M.A., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. CoRR (2014)","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"26_CR23","unstructured":"El-Nouby, A., Izacard, G., Touvron, H., Laptev, I., Jegou, H., Grave, E.: Are large-scale datasets necessary for self-supervised pre-training? arXiv preprint arXiv:2112.10740 (2021)"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Goyal, P., Mahajan, D., Gupta, A., Misra, I.: Scaling and benchmarking self-supervised visual representation learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00649"},{"key":"26_CR25","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. In: NeurIPS (2020)"},{"key":"26_CR26","unstructured":"Gupta, K., Somepalli, G., Anubhav, A., Magalle Hewa, V.Y.J., Zwicker, M., Shrivastava, A.: PatchGame: learning to signal mid-level patches in referential games. In: Advances in Neural Information Processing Systems, vol. 34, pp. 26015\u201326027 (2021)"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"26_CR28","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":"26_CR29","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":"26_CR30","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"26_CR31","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: Proceedings of the International Conference on Learning Representations (2019)"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"26_CR33","unstructured":"Joulin, A., Bach, F.: A convex relaxation for weakly supervised classifiers. arXiv preprint arXiv:1206.6413 (2012)"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Colorization as a proxy task for visual understanding. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.96"},{"key":"26_CR36","unstructured":"Li, C., et al.: Efficient self-supervised vision transformers for representation learning. arXiv preprint arXiv:2106.09785 (2021)"},{"key":"26_CR37","first-page":"13165","volume":"34","author":"Z Li","year":"2021","unstructured":"Li, Z., et al.: MST: masked self-supervised transformer for visual representation. Adv. Neural. Inf. Process. Syst. 34, 13165\u201313176 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR38","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Lucas, T., Weinzaepfel, P., Rogez, G.: Barely-supervised learning: semi-supervised learning with very few labeled images. preprint arXiv:2112.12004 (2021)","DOI":"10.1609\/aaai.v36i2.20082"},{"key":"26_CR40","unstructured":"Mairal, J.: Cyanure: an open-source toolbox for empirical risk minimization for Python, C++, and soon more. arXiv preprint arXiv:1912.08165 (2019)"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"26_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by Solving Jigsaw Puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.278"},{"issue":"3","key":"26_CR44","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"26_CR45","unstructured":"Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685 (2020)"},{"key":"26_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-030-58621-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776\u2013794. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_45"},{"key":"26_CR47","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"26_CR48","unstructured":"Trinh, T.H., Luong, M.T., Le, Q.V.: Selfie: self-supervised pretraining for image embedding. arXiv preprint arXiv:1906.02940 (2019)"},{"key":"26_CR49","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"26_CR50","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A., Bottou, L.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(12) (2010)"},{"key":"26_CR51","unstructured":"Wang, H., Ge, S., Lipton, Z., Xing, E.P.: Learning robust global representations by penalizing local predictive power. In: Advances in Neural Information Processing Systems, pp. 10506\u201310518 (2019)"},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. arXiv preprint arXiv:2112.09133 (2021)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"26_CR53","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"26_CR54","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, M.T., Le, Q.V.: Unsupervised data augmentation. arXiv preprint arXiv:1904.12848 (2019)"},{"key":"26_CR55","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. arXiv preprint arXiv:2111.09886 (2021)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"26_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. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"26_CR57","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. arXiv preprint arXiv:2103.03230 (2021)"},{"key":"26_CR58","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"26_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"key":"26_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Split-brain autoencoders: unsupervised learning by cross-channel prediction. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.76"},{"key":"26_CR61","unstructured":"Zhou, J., et al.: iBOT: image BERT pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)"},{"key":"26_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, R., Zhao, B., Liu, J., Sun, Z., Chen, C.W.: Improving contrastive learning by visualizing feature transformation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10306\u201310315 (2021)","DOI":"10.1109\/ICCV48922.2021.01014"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19821-2_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:53:47Z","timestamp":1666443227000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19821-2_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198205","9783031198212"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19821-2_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}