{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T10:12:17Z","timestamp":1780395137407,"version":"3.54.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0711404"],"award-info":[{"award-number":["2022YFF0711404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20201250"],"award-info":[{"award-number":["BK20201250"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62172090"],"award-info":[{"award-number":["62172090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAAI-Huawei MindSpore Open Fund"},{"name":"Nanjing Municipal Program for Technological Innovation by Overseas Scholars","award":["1109012301"],"award-info":[{"award-number":["1109012301"]}]},{"DOI":"10.13039\/501100008081","name":"Start-Up Research Fund of Southeast University","doi-asserted-by":"publisher","award":["RF1028623097"],"award-info":[{"award-number":["RF1028623097"]}],"id":[{"id":"10.13039\/501100008081","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3276708","type":"journal-article","created":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T18:02:10Z","timestamp":1685037730000},"page":"3442-3454","source":"Crossref","is-referenced-by-count":11,"title":["Learning the Relation Between Similarity Loss and Clustering Loss in Self-Supervised Learning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1773-0942","authenticated-orcid":false,"given":"Jidong","family":"Ge","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Software Institute, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Software Institute, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9450-1759","authenticated-orcid":false,"given":"Jie","family":"Gui","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanting","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Lin","sequence":"additional","affiliation":[{"name":"Alibaba Group, Bellevue, WA, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4828-8248","authenticated-orcid":false,"given":"James Tin-Yau","family":"Kwok","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liguo","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Southern Methodist University, Dallas, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Software Institute, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hjelm"},{"key":"ref2","article-title":"Representation learning with contrastive predictive coding","author":"Van Den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref3","first-page":"15535","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Bachman"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00305"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref7","first-page":"1","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Brown"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref9","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henaff"},{"key":"ref10","first-page":"12310","article-title":"Barlow Twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Zbontar"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref12","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021","journal-title":"arXiv:2111.06377"},{"key":"ref13","first-page":"517","article-title":"Unsupervised learning by predicting noise","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bojanowski"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496141"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref16","first-page":"15614","article-title":"Parametric instance classification for unsupervised visual feature learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Cao"},{"key":"ref17","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Tian"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref20","article-title":"BYOL works even without batch statistics","author":"Richemond","year":"2020","journal-title":"arXiv:2010.10241"},{"key":"ref21","article-title":"Understanding self-supervised learning with dual deep networks","author":"Tian","year":"2020","journal-title":"arXiv:2010.00578"},{"key":"ref22","first-page":"10268","article-title":"Understanding self-supervised learning dynamics without contrastive pairs","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Tian"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref26","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","volume":"48","author":"Xie"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00654"},{"key":"ref28","first-page":"2849","article-title":"Unsupervised deep learning by neighbourhood discovery","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref30","first-page":"1","article-title":"Self-labelling via simultaneous clustering and representation learning","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Asano"},{"key":"ref31","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Caron"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17037"},{"key":"ref33","first-page":"10990","article-title":"Distilling localization for self-supervised representation learning","volume-title":"Proc. 35th AAAI Conf. Artif. Intell. (AAAI), 33rd Conf. Innov. Appl. Artif. Intell. (IAAI), 11th Symp. Educ. Adv. Artif. Intell. (EAAI)","author":"Zhao"},{"key":"ref34","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"26","author":"Cuturi"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref36","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Wang"},{"key":"ref37","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"issue":"11","key":"ref39","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","volume-title":"The Imagenette Dataset","author":"Howard","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref42","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref44","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref45","first-page":"6","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (ICML)","author":"Ioffe"},{"key":"ref46","article-title":"Large batch training of convolutional networks","author":"You","year":"2017","journal-title":"arXiv:1708.03888"},{"key":"ref47","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref48","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref49","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"28","author":"Ren"},{"key":"ref50","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00649"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref55","volume-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"ref57","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist. (AISTATS)","volume":"9","author":"Glorot"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10136584.pdf?arnumber=10136584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T01:59:51Z","timestamp":1710381591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10136584\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3276708","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}