{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T08:44:41Z","timestamp":1748249081250,"version":"3.37.3"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"European Commission under European Horizon 2020 Programme","award":["951911"],"award-info":[{"award-number":["951911"]}]},{"name":"CINECA"},{"name":"CINECA award under the ISCRA initiative","award":["HP10CRMI87"],"award-info":[{"award-number":["HP10CRMI87"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tpami.2023.3259542","type":"journal-article","created":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T17:47:09Z","timestamp":1679334429000},"page":"9567-9582","source":"Crossref","is-referenced-by-count":2,"title":["CoReS: Compatible Representations via Stationarity"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1153-1651","authenticated-orcid":false,"given":"Niccol\u00f2","family":"Biondi","sequence":"first","affiliation":[{"name":"Dipartimento di Ingegneria dell’Informazione, Media Integration and Communication Center (MICC), Università degli Studi di Firenze, Firenze, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7036-6655","authenticated-orcid":false,"given":"Federico","family":"Pernici","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria dell’Informazione, Media Integration and Communication Center (MICC), Università degli Studi di Firenze, Firenze, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2017-1061","authenticated-orcid":false,"given":"Matteo","family":"Bruni","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria dell’Informazione, Media Integration and Communication Center (MICC), Università degli Studi di Firenze, Firenze, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-8322","authenticated-orcid":false,"given":"Alberto","family":"Del Bimbo","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria dell’Informazione, Media Integration and Communication Center (MICC), Università degli Studi di Firenze, Firenze, Italy"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICCV.2019.00844"},{"year":"2009","author":"krizhevsky","article-title":"Learning multiple layers of features from tiny images","key":"ref57"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR.2017.357"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1109\/TPAMI.2017.2773081"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1007\/978-3-319-46466-4_15"},{"year":"2007","author":"huang","article-title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","key":"ref59"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/978-3-319-10590-1_38"},{"year":"2014","author":"yi","article-title":"Learning face representation from scratch","key":"ref58"},{"key":"ref53","article-title":"Fix your classifier: The marginal value of training the last weight layer","author":"hoffer","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref52","article-title":"Identity matters in deep learning","author":"hardt","year":"2017","journal-title":"Proc 5th Int Conf Learn Representations"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR.2014.27"},{"key":"ref55","first-page":"985","article-title":"Covariate shift adaptation by importance weighted cross validation","volume":"8","author":"sugiyama","year":"2007","journal-title":"J Mach Learn Res"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICPR.2014.16"},{"year":"2009","author":"qui\u00f1onero-candela","journal-title":"Dataset Shift in Machine Learning","key":"ref54"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1016\/j.cviu.2019.03.001"},{"key":"ref16","first-page":"1","article-title":"Particular object retrieval with integral max-pooling of CNN activations","author":"tolias","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1038\/d41586-020-03187-3"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR42600.2020.00640"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref50","first-page":"507","article-title":"Large-margin softmax loss for convolutional neural networks","author":"liu","year":"2016","journal-title":"Proc 33nd Int Conf Mach Learn"},{"year":"2019","author":"van de ven","article-title":"Three scenarios for continual learning","key":"ref46"},{"key":"ref45","article-title":"Re-evaluating continual learning scenarios: A categorization and case for strong baselines","author":"hsu","year":"2018","journal-title":"Proc NeurIPS Continual Learn Workshop"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.1016\/S0079-7421(08)60536-8"},{"year":"2020","author":"masana","article-title":"Class-incremental learning: Survey and performance evaluation","key":"ref47"},{"key":"ref42","first-page":"19553","article-title":"Maximum separation as inductive bias in one matrix","author":"kasarla","year":"2022","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref41","first-page":"37991","article-title":"Inducing neural collapse in imbalanced learning: Do we really need a learnable classifier at the end of deep neural network?","author":"yang","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","article-title":"The met dataset: Instance-level recognition for artworks","author":"ypsilantis","year":"2021","journal-title":"Proc 35th Conf Neural Inf Process Syst Datasets Benchmarks Track"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/CVPR42600.2020.00265"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref8","first-page":"1988","article-title":"Deep learning face representation by joint identification-verification","author":"sun","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2014.220"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref4","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref6","first-page":"507","article-title":"Large-margin softmax loss for convolutional neural networks","author":"liu","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR.2015.7298682"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1073\/pnas.2103091118"},{"key":"ref35","first-page":"9607","article-title":"Towards understanding learning representations: To what extent do different neural networks learn the same representation","author":"wang","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref34","first-page":"196","article-title":"Convergent learning: Do different neural networks learn the same representations?","author":"li","year":"2015","journal-title":"Proc 1st Int Workshop Feature Extraction Modern Questions Challenges"},{"year":"2022","author":"kothapalli","article-title":"Neural collapse: A review on modelling principles and generalization","key":"ref37"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1073\/pnas.2015509117"},{"key":"ref31","first-page":"116","article-title":"Backward-compatible prediction updates: A probabilistic approach","author":"tr\u00e4uble","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/CVPR46437.2021.01407"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/CVPR46437.2021.00813"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1609\/aaai.v35i9.16932"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TPAMI.2013.50"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref39","first-page":"29820","article-title":"A geometric analysis of neural collapse with unconstrained features","author":"zhu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"3821","article-title":"Dissecting supervised constrastive learning","author":"graf","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref71","first-page":"529","article-title":"Simplifying neural nets by discovering flat minima","author":"hochreiter","year":"1995","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref70","article-title":"What is being transferred in transfer learning?","author":"neyshabur","year":"2020","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref72","DOI":"10.1162\/neco.1997.9.1.1"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICCV48922.2021.00979"},{"key":"ref68","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":"ref23","article-title":"Unified representation learning for cross model compatibility","author":"wang","year":"2020","journal-title":"Proc 31st Brit Mach Vis Conf"},{"key":"ref67","article-title":"Understanding dimensional collapse in contrastive self-supervised learning","author":"jing","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","first-page":"46","article-title":"Maximally compact and separated features with regular polytope networks","author":"pernici","year":"2019","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit Workshops"},{"key":"ref25","first-page":"6259","article-title":"Class-incremental learning with pre-allocated fixed classifiers","author":"pernici","year":"2020","journal-title":"Proc 25th Int Conf Pattern Recognit"},{"key":"ref69","article-title":"Uniform convergence may be unable to explain generalization in deep learning","author":"nagarajan","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR46437.2021.01058"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"year":"2019","author":"zhou","article-title":"Torchreid: A library for deep learning person re-identification in PyTorch","key":"ref63"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR.2019.00312"},{"key":"ref66","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR.2019.01010"},{"doi-asserted-by":"publisher","key":"ref65","DOI":"10.1109\/TBDATA.2019.2921572"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1609\/aaai.v33i01.33012429"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/TNNLS.2021.3056762"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1145\/3394486.3403379"},{"doi-asserted-by":"publisher","key":"ref60","DOI":"10.1109\/ICCV.2015.133"},{"doi-asserted-by":"publisher","key":"ref62","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"publisher","key":"ref61","DOI":"10.1109\/TPAMI.2019.2913372"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10169863\/10077426.pdf?arnumber=10077426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:40:36Z","timestamp":1689615636000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10077426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":72,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3259542","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}