{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:27:55Z","timestamp":1777865275410,"version":"3.51.4"},"reference-count":73,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02176","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23442-23452","source":"Crossref","is-referenced-by-count":0,"title":["Beyond [cls]: Exploring the True Potential of Masked Image Modeling Representations"],"prefix":"10.1109","author":[{"given":"Marcin","family":"Przewiezlikowski","sequence":"first","affiliation":[{"name":"Jagiellonian University,Faculty of Mathematics and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Randall","family":"Balestriero","sequence":"additional","affiliation":[{"name":"Brown University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wojciech","family":"Jasinski","sequence":"additional","affiliation":[{"name":"Jagiellonian University,Faculty of Mathematics and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marek","family":"Smieja","sequence":"additional","affiliation":[{"name":"Jagiellonian University,Faculty of Mathematics and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bartosz","family":"Zielinski","sequence":"additional","affiliation":[{"name":"Jagiellonian University,Faculty of Mathematics and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/e24040551"},{"key":"ref2","article-title":"MIM-refiner: A contrastive learning boost from intermediate pre-trained masked image modeling representations","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Alkin"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref4","article-title":"The hidden uniform cluster prior in self-supervised learning","volume-title":"In The Eleventh International Conference on Learning Representations","volume":"1","author":"Assran"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref6","article-title":"Sit: Self-supervised vision transformer","volume":"1","author":"Atito","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","author":"Lei Ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref8","article-title":"others. Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2015","journal-title":"ICLR"},{"issue":"2","key":"ref9","article-title":"How learning by reconstruction produces uninformative features for perception","volume-title":"Forty-first International Conference on Machine Learning","volume":"1","author":"Balestriero"},{"key":"ref10","article-title":"A cookbook of self-supervised learning","author":"Balestriero","year":"2023","journal-title":"ArXiv, abs\/2304.12210"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24894\/sprengglossarium_b03425"},{"key":"ref12","author":"Bardes","year":"2024","journal-title":"Revisiting feature prediction for learning visual representations from video"},{"key":"ref13","article-title":"Guillotine regularization: Why removing layers is needed to improve generalization in selfsupervised learning","author":"Bordes","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"issue":"2","key":"ref15","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"In Advances in Neural Information Processing Systems","volume":"1","author":"Caron","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref17","article-title":"Amortised invariance learning for contrastive self-supervision","volume-title":"The Eleventh International Conference on Learning Representations","volume":"2","author":"Chavhan"},{"key":"ref18","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"In Proceedings of the 37th International Conference on Machine Learning","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref20","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"CoRR, abs\/2003.04297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02801"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00176"},{"key":"ref27","author":"Darcet","year":"2025","journal-title":"Cluster and predict latents patches for improved masked image modeling"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"ref31","volume":"2","author":"Garrido","year":"2024","journal-title":"Learning and leveraging world models in visual representation learning"},{"key":"ref32","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"International Conference on Learning Representations","author":"Gidaris"},{"key":"ref33","article-title":"Large batch training of convolutional networks with layer-wise adaptive rate scaling","author":"Ginsburg","year":"2018","journal-title":"13"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref38","article-title":"How transformers learn diverse attention correlations in masked vision pretraining","volume-title":"ICML 2024 Workshop on Theoretical Foundations of Foundation Models","volume":"2","author":"Huang","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00604"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref41","first-page":"17710","article-title":"Improving transferability of representations via augmentation-aware self-supervision","author":"Lee","year":"2021","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","article-title":"Attention-based deep multiple instance learning","author":"Ilse","year":"2018","journal-title":"ICML"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref45","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"ArXiv, abs\/2304.07193"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/145"},{"key":"ref47","volume-title":"What do self-supervised vision transformers learn? In The Eleventh International Conference on Learning Representations","volume":"1","author":"Park"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref49","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24894\/sprengglossarium_b03425"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112572"},{"key":"ref52","first-page":"5350","volume-title":"Keep it simpool: Who said supervised transformers suffer from attention deficit? In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Psomas"},{"key":"ref53","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1879"},{"key":"ref56","first-page":"6827","volume":"33","author":"Tian","year":"2020","journal-title":"What makes for good views for contrastive learning?"},{"key":"ref57","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems. Curran Associates, Inc."},{"key":"ref58","article-title":"Is imagenet worth 1 video? learning strong image encoders from 1 long unlabelled video","volume-title":"The Twelfth International Conference on Learning Representations","author":"Venkataramanan"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"issue":"12","key":"ref60","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"Journal of machine learning research"},{"key":"ref61","article-title":"The Caltech-UCSD Birds-200\u20132011 Dataset","volume-title":"Technical Report CNS-TR-2011-001, California Institute of Technology","volume":"7","author":"Wah","year":"2011"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01426"},{"key":"ref63","article-title":"What should not be contrastive in contrastive learning","volume-title":"International Conference on Learning Representations","author":"Xiao"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"ref66","article-title":"Exploring target representations for masked autoencoders","volume-title":"The Twelfth International Conference on Learning Representations","author":"liu"},{"key":"ref67","article-title":"How transferable are features in deep neural networks?","volume-title":"In Advances in Neural Information Processing Systems","author":"Yosinski","year":"2014"},{"key":"ref68","author":"Yuan","year":"2025","journal-title":"SemanticMIM: Marring masked image modeling with semantics compression for general visual representation"},{"key":"ref69","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Zbontar"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1967"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref72","article-title":"Image BERT pre-training with online tokenizer","volume-title":"International Conference on Learning Representations","author":"Zhou"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2025.3564382"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443292.pdf?arnumber=11443292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:10:11Z","timestamp":1777529411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02176","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}