{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T19:21:24Z","timestamp":1783192884359,"version":"3.54.6"},"reference-count":136,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021YFB3100800"],"award-info":[{"award-number":["2021YFB3100800"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225604"],"award-info":[{"award-number":["62225604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376283"],"award-info":[{"award-number":["62376283"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Supercomputing Center of Nankai University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2025.3558989","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T17:39:46Z","timestamp":1744133986000},"page":"5976-5989","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Representations Through Heterogeneous Self-Supervised Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3682-4904","authenticated-orcid":false,"given":"Zhong-Yu","family":"Li","sequence":"first","affiliation":[{"name":"VCIP & TBI Center, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0247-8202","authenticated-orcid":false,"given":"Bo-Wen","family":"Yin","sequence":"additional","affiliation":[{"name":"VCIP & TBI Center, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0682-8365","authenticated-orcid":false,"given":"Yongxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2011-2873","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-8758","authenticated-orcid":false,"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"VCIP & TBI Center, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref4","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"ref7","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3309979"},{"key":"ref9","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Caron"},{"key":"ref10","article-title":"iBOT: Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00068"},{"key":"ref18","article-title":"ConTNet: Why not use convolution and transformer at the same time?","author":"Yan","year":"2021"},{"key":"ref19","first-page":"4193","article-title":"Revitalizing CNN attentions via transformers in self-supervised visual representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ge"},{"key":"ref20","article-title":"Dformer: Rethinking RGBD representation learning for semantic segmentation","author":"Yin","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3218275"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00299"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref30","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.628"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01000"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01016"},{"key":"ref39","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dosovitskiy"},{"key":"ref40","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00605"},{"key":"ref43","article-title":"Efficient self-supervised vision pretraining with local masked reconstruction","author":"Chen","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01450"},{"key":"ref45","article-title":"Corrupted image modeling for self-supervised visual pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00120"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00993"},{"key":"ref48","article-title":"Mugs: A multi-granular self-supervised learning framework","author":"Zhou","year":"2022"},{"key":"ref49","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_38"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref55","first-page":"10268","article-title":"Understanding self-supervised learning dynamics without contrastive pairs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tian"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref57","first-page":"3015","article-title":"Whitening for self-supervised representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ermolov"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref60","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00616"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00305"},{"key":"ref63","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref64","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bardes"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01508"},{"key":"ref66","article-title":"Towards sustainable self-supervised learning","author":"Gao","year":"2022"},{"key":"ref67","article-title":"Self-labelling via simultaneous clustering and representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Asano"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/200"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01475"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_27"},{"key":"ref71","first-page":"4489","article-title":"Unsupervised learning of dense visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinheiro"},{"key":"ref72","first-page":"28864","article-title":"Unsupervised object-level representation learning from scene images","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01405"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"ref75","first-page":"13165","article-title":"MST: Masked self-supervised transformer for visual representation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref76","article-title":"Efficient self-supervised vision transformers for representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01001"},{"key":"ref79","first-page":"14290","article-title":"SemMAE: Semantic-guided masking for learning masked autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref80","article-title":"Masked frequency modeling for self-supervised visual pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00494"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00211"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25252"},{"key":"ref86","first-page":"46134","article-title":"DropPos: Pre-training vision transformers by reconstructing dropped positions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref87","article-title":"Masked image modeling with denoising contrast","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_7"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01898-4"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_15"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref96","article-title":"Exploring target representations for masked autoencoders","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref98","article-title":"Extreme masking for learning instance and distributed visual representations","author":"Wu","year":"2022"},{"key":"ref99","article-title":"Layer grafted pre-training: Bridging contrastive learning and masked image modeling for label-efficient representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jiang"},{"key":"ref100","first-page":"20026","article-title":"Adversarial masking for self-supervised learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shi"},{"key":"ref101","article-title":"Contextual image masking modeling via synergized contrasting without view augmentation for faster and better visual pretraining","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref103","first-page":"19997","article-title":"Green hierarchical vision transformer for masked image modeling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref104","first-page":"35632","article-title":"MCMAE: Masked convolution meets masked autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gao"},{"key":"ref105","article-title":"Uniform masking: Enabling mae pre-training for pyramid-based vision transformers with locality","author":"Li","year":"2022"},{"key":"ref106","article-title":"Designing BERT for convolutional networks: Sparse and hierarchical masked modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01785"},{"key":"ref108","article-title":"A unified view of masked image modeling","author":"Peng","year":"2022"},{"key":"ref109","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109228"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3438565"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref119","article-title":"Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mehta"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00123"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01140"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref124","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref125","first-page":"28243","article-title":"Cascade-CLIP: Cascaded vision-language embeddings alignment for zero-shot semantic segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"ref130","article-title":"Towards raw object detection in diverse conditions","author":"Li","year":"2024"},{"key":"ref131","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref135","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Raghu"},{"key":"ref136","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kornblith"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10955443.pdf?arnumber=10955443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:41:53Z","timestamp":1749231713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955443\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":136,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3558989","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":[[2025,7]]}}}