{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T17:23:38Z","timestamp":1782926618215,"version":"3.54.5"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R01EB031102"],"award-info":[{"award-number":["R01EB031102"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471148"],"award-info":[{"award-number":["62471148"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2025.3648138","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:36Z","timestamp":1768255476000},"page":"332-345","source":"Crossref","is-referenced-by-count":1,"title":["Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3310-7803","authenticated-orcid":false,"given":"Chuang","family":"Niu","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0604-3197","authenticated-orcid":false,"given":"Hongming","family":"Shan","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology for Brain-Inspired Intelligence, the MOE Frontiers Center for Brain Science, and the Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2656-7705","authenticated-orcid":false,"given":"Ge","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-56822-w"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3026622"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3231428"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3142999"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_44"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3221290"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3346295"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref11","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gidaris"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2993403"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3011269"},{"key":"ref14","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","volume":"27","author":"Dosovitskiy"},{"key":"ref15","article-title":"To compress or not to compress-self-supervised learning and information theory: A review","author":"Shwartz-Ziv","year":"2023","journal-title":"arXiv:2304.09355"},{"key":"ref16","first-page":"6827","article-title":"What makes for good views for contrastive learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Tian"},{"key":"ref17","first-page":"35240","article-title":"Self-supervised learning with an information maximization criterion","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Ozsoy"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3985"},{"key":"ref19","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Henaff"},{"key":"ref20","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref21","article-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv","year":"2017","journal-title":"arXiv:1703.00810"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35749-7_1"},{"key":"ref23","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv:1611.01144"},{"key":"ref24","first-page":"1","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Maddison"},{"key":"ref25","article-title":"Learning deep representations by mutual information estimation and maximization","author":"Devon Hjelm","year":"2018","journal-title":"arXiv:1808.06670"},{"issue":"1","key":"ref26","first-page":"47","article-title":"Discretization techniques: A recent survey","volume":"32","author":"Kotsiantis","year":"2006","journal-title":"GESTS Int. Trans. Comput. Sci. Eng."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.35"},{"key":"ref28","first-page":"4153","article-title":"Estimating information flow in deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goldfeld"},{"key":"ref29","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref30","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref31","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"van den"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref36","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00305"},{"key":"ref39","article-title":"Self-labelling via simultaneous clustering and representation learning","author":"Markus Asano","year":"2019","journal-title":"arXiv:1911.05371"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00654"},{"key":"ref41","first-page":"2849","article-title":"Unsupervised deep learning by neighbourhood discovery","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00610"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00676"},{"key":"ref44","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref45","article-title":"BYOL works even without batch statistics","author":"Richemond","year":"2020","journal-title":"arXiv:2010.10241"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref47","first-page":"3015","article-title":"Whitening for self-supervised representation learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Ermolov"},{"key":"ref48","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":"ref49","first-page":"1","article-title":"How does SimSiam avoid collapse without negative samples? A unified understanding with self-supervised contrastive learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref50","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":"ref51","article-title":"Contrastive and non-contrastive self-supervised learning recover global and local spectral embedding methods","author":"Balestriero","year":"2022","journal-title":"arXiv:2205.11508"},{"key":"ref52","first-page":"1","article-title":"On the duality between contrastive and non-contrastive self-supervised learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Garrido"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1147\/rd.41.0066"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00946"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","article-title":"Large batch training of convolutional networks","author":"You","year":"2017","journal-title":"arXiv:1708.03888"},{"key":"ref57","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref58","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref59","first-page":"11279","article-title":"Improving self-supervised learning by characterizing idealized representations","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Dubois"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref61","volume-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref63","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref64","volume-title":"MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark","year":"2020"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref66","first-page":"1","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICICCT.2018.8473136"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714567"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681415"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33319"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736877"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11339363.pdf?arnumber=11339363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:22Z","timestamp":1770671422000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3648138","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}