{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:15:49Z","timestamp":1765041349435,"version":"3.37.3"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3220928","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T20:37:53Z","timestamp":1668112673000},"page":"1-19","source":"Crossref","is-referenced-by-count":7,"title":["Dynamic Self-Supervised Teacher-Student Network Learning"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5894-2178","authenticated-orcid":false,"given":"Fei","family":"Ye","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of York, York, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7838-0021","authenticated-orcid":false,"given":"Adrian G.","family":"Bors","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of York, York, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref5","first-page":"11816","article-title":"Gradient based sample selection for online continual learning","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","author":"Aljundi"},{"article-title":"Efficient lifelong learning with A-GEM","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chaudhry","key":"ref6"},{"article-title":"On tiny episodic memories in continual learning","year":"2019","author":"Chaudhry","key":"ref7"},{"key":"ref8","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lopez-Paz"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058852"},{"key":"ref10","first-page":"9873","article-title":"Life-long disentangled representation learning with cross-domain latent homologies","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","author":"Achille"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.115"},{"key":"ref12","first-page":"7645","article-title":"Continual unsupervised representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref13","first-page":"2990","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","author":"Shin"},{"key":"ref14","first-page":"5962","article-title":"Memory replay GANs: Learning to generate new categories without forgetting","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","author":"Wu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00285"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"ref17","first-page":"3308","article-title":"VEEGAN: Reducing mode collapse in GANs using implicit variational learning","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","author":"Srivastava"},{"article-title":"A neural dirichlet process mixture model for task-free continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20867"},{"article-title":"Learning in implicit generative models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mohamed","key":"ref20"},{"key":"ref21","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013771"},{"article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn. Workshop","author":"Hinton","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref26","article-title":"Ensemble distribution distillation","author":"Andrey Malinin","year":"2020","journal-title":"Proc. Int. Conf. Learn. Representations"},{"article-title":"Efficient evaluation-time uncertainty estimation by improved distillation","volume-title":"Proc. Workshop Uncertainty Robustness Deep Learn.","author":"Englesson","key":"ref27"},{"key":"ref28","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00276"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3092677"},{"key":"ref31","first-page":"874","article-title":"AdaNet: Adaptive structural learning of artificial neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cortes"},{"key":"ref32","first-page":"13669","article-title":"Compacting, picking and growing for unforgetting continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hung"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/5326.983933"},{"article-title":"Progressive neural networks","year":"2016","author":"Rusu","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654926"},{"key":"ref37","first-page":"1453","article-title":"Online incremental feature learning with denoising autoencoders","volume-title":"Proc. Artif. Intell. Statist.","author":"Zhou"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071401"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IPTA50016.2020.9286619"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3096457"},{"article-title":"BatchEnsemble: An alternative approach to efficient ensemble and lifelong learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wen","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01052"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IPTA50016.2020.9286663"},{"key":"ref44","first-page":"4453","article-title":"Continual deep learning by functional regularisation of memorable past","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_46"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506116"},{"article-title":"GAN Wasserstein","year":"2017","author":"Arjovsky","key":"ref47"},{"key":"ref48","first-page":"5769","article-title":"Improved training of wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","author":"Gulrajani"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238387"},{"key":"ref50","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belghazi"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00493"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref53","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yosinski"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/0047-259X(82)90077-X"},{"key":"ref55","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref56","first-page":"775","article-title":"KDGAN: Knowledge distillation with generative adversarial networks","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","author":"Wang"},{"volume-title":"Statistical Theory of Extreme Values and Some Practical Applications: A Series of Lectures","year":"1954","author":"Gumbel","key":"ref57"},{"key":"ref58","first-page":"1","article-title":"A*sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Maddison"},{"key":"ref59","first-page":"708","article-title":"Learning disentangled joint continuous and discrete representations","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","author":"Dupont"},{"key":"ref60","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2017","journal-title":"Proc. Int. Conf. Learn. Representations"},{"article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Maddison","key":"ref61"},{"key":"ref62","article-title":"Lagging inference networks and posterior collapse in variational autoencoders","author":"He","year":"2019","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref65","first-page":"5142","article-title":"Towards understanding knowledge distillation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Phuong"},{"article-title":"Understanding disentangling in \u03b2-vae","volume-title":"Proc. NIPS Workshop Learn. Disentangled Representation","author":"Burgess","key":"ref66"},{"key":"ref67","first-page":"2615","article-title":"Isolating sources of disentanglement in variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","author":"Chen"},{"key":"ref68","first-page":"1157","article-title":"Auto-Encoding Total Correlation Explanation","volume-title":"Proc. Int. Conf. On Artif. Intel. Statist. 2018","author":"Gao"},{"key":"ref69","first-page":"1","article-title":"\u03b2-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins"},{"key":"ref70","first-page":"2649","article-title":"Disentangling by factorising","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref71","first-page":"8281","article-title":"Autoencoder image interpolation by shaping the latent space","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oring"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","key":"ref72"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","year":"2017","author":"Xiao","key":"ref74"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref77","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Univ. Toronto, Tech. Rep"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.03.007"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_49"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.487"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref84","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref85"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09944861.pdf?arnumber=9944861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:02:31Z","timestamp":1706756551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9944861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3220928","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":[[2022]]}}}