{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:52:50Z","timestamp":1780764770814,"version":"3.54.1"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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":["62176130"],"award-info":[{"award-number":["62176130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities, Nankai Universitiy","award":["070-63233089"],"award-info":[{"award-number":["070-63233089"]}]},{"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":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3309979","type":"journal-article","created":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T17:22:57Z","timestamp":1693416177000},"page":"15619-15631","source":"Crossref","is-referenced-by-count":16,"title":["SERE: Exploring Feature Self-Relation for Self-Supervised Transformer"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3682-4904","authenticated-orcid":false,"given":"Zhong-Yu","family":"Li","sequence":"first","affiliation":[{"name":"TMCC, CS, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7055-2703","authenticated-orcid":false,"given":"Shanghua","family":"Gao","sequence":"additional","affiliation":[{"name":"TMCC, CS, Nankai University, Tianjin, 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":"TMCC, CS, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","article-title":"Efficient self-supervised vision transformers for representation learning","author":"li","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref56","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","first-page":"13165","article-title":"MST: Masked self-supervised transformer for visual representation","author":"li","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","article-title":"Mugs: A multi-granular self-supervised learning framework","author":"zhou","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref52","first-page":"1144","article-title":"Spatilly consistent representation learning","author":"roh","year":"2021","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3202765"},{"key":"ref54","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","author":"cheng","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"ref46","first-page":"10268","article-title":"Understanding self-supervised learning dynamics without contrastive pairs","author":"tian","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","first-page":"3015","article-title":"Whitening for self-supervised representation learning","author":"ermolov","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00113"},{"key":"ref47","article-title":"Revitalizing CNN attentions via transformers in self-supervised visual representation learning","author":"ge","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"ref41","first-page":"139","article-title":"Deep clustering for unsupervised learning of visual features","author":"caron","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01016"},{"key":"ref43","article-title":"Self-labelling via simultaneous clustering and representation learning","author":"yuki markus","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3535-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"caron","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref6","first-page":"21271","article-title":"Bootstrap your own latent - a new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00944"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1430-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.628"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01000"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref30","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1406-4"},{"key":"ref38","article-title":"Decoupled contrastive learning","author":"yeh","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00342"},{"key":"ref26","article-title":"Large-scale unsupervised semantic segmentation","author":"gao","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref22","article-title":"Do vision transformers see like convolutional neural networks?","author":"raghu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","first-page":"10086","article-title":"Efficient visual pretraining with contrastive detection","author":"h\u00e9naff","year":"2021","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref12","first-page":"9992","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"liu","year":"2021","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref97","first-page":"418","article-title":"Unified perceptual parsing for scene understanding","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref99","first-page":"3407","article-title":"Demystifying contrastive self-supervised learning: Invariances, augmentations and dataset biases","author":"purushwalkam shiva prakash","year":"2020","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref10","first-page":"2984","article-title":"RF-Next: Efficient receptive field search for convolutional neural networks","volume":"45","author":"gao","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1386-4"},{"key":"ref16","article-title":"Self-supervised learning with swin transformers","author":"xie","year":"2021"},{"key":"ref19","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","article-title":"iBOT: Image bert pre-training with online tokenizer","author":"zhou","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref93","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref92","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref91","first-page":"84","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00816"},{"key":"ref89","article-title":"Deep learning using rectified linear units (RELU)","author":"agarap","year":"2018"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref85","first-page":"262","article-title":"Texture synthesis using convolutional neural networks","author":"gatys","year":"2015","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref88","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref87","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"zbontar","year":"2021"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00280"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01414"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_48"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"ref80","article-title":"Localizing objects with self-supervised transformers and no labels","author":"sim\u00e9oni","year":"2021","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00194"},{"key":"ref78","article-title":"Unsupervised semantic segmentation by distilling feature correspondences","author":"hamilton","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.149"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11783"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"ref102","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","author":"bardes","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00067"},{"key":"ref103","article-title":"Why do self-supervised models transfer? Investigating the impact of invariance on downstream tasks","author":"ericsson","year":"2022","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref2","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref73","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_2"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref67","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/200"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref66","article-title":"Masked feature prediction for self-supervised visual pre-training","author":"wei","year":"2021"},{"key":"ref65","article-title":"SiT: Self-supervised vision transformer","author":"atito","year":"2021"},{"key":"ref60","article-title":"BEit: BERT pre-training of image transformers","author":"bao","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref62","article-title":"Context autoencoder for self-supervised representation learning","author":"chen","year":"2022"},{"key":"ref61","article-title":"Towards sustainable self-supervised learning","author":"gao","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10234504.pdf?arnumber=10234504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:46:39Z","timestamp":1701114399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10234504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":104,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3309979","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":[[2023,12]]}}}