{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T21:58:50Z","timestamp":1770328730921,"version":"3.49.0"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021YFA1000403"],"award-info":[{"award-number":["2021YFA1000403"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11991022"],"award-info":[{"award-number":["11991022"]}],"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":["U19B2040"],"award-info":[{"award-number":["U19B2040"]}],"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":["U22B2049"],"award-info":[{"award-number":["U22B2049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA27000000"],"award-info":[{"award-number":["XDA27000000"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tnnls.2023.3241791","type":"journal-article","created":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T18:30:51Z","timestamp":1675967451000},"page":"10407-10421","source":"Crossref","is-referenced-by-count":5,"title":["STDNet: Rethinking Disentanglement Learning With Information Theory"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3894-1677","authenticated-orcid":false,"given":"Ziwen","family":"Liu","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Mingqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Information Science Academy, China Electronics Technology Group Corporation, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3445-4620","authenticated-orcid":false,"given":"Congying","family":"Han","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Siqi","family":"Tang","sequence":"additional","affiliation":[{"name":"Information Science Academy, China Electronics Technology Group Corporation, Beijing, China"}]},{"given":"Tiande","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021","journal-title":"arXiv:2111.06377"},{"key":"ref5","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref7","first-page":"613","article-title":"Generating videos with scene dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vondrick"},{"key":"ref8","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"Lotter","year":"2016","journal-title":"arXiv:1605.08104"},{"key":"ref9","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref11","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref12","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref14","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Hassani"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11301"},{"key":"ref16","first-page":"1","article-title":"Capturing label characteristics in VAEs","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Joy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380112"},{"key":"ref18","first-page":"2172","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref19","first-page":"2649","article-title":"Disentangling by factorising","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref20","first-page":"1","article-title":"SS -VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. ICLR","author":"Higgins"},{"key":"ref21","article-title":"Understanding disentangling in \u03b2-VAE","author":"Burgess","year":"2018","journal-title":"arXiv:1804.03599"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00665"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00095"},{"key":"ref26","first-page":"1","article-title":"Image-to-image translation for cross-domain disentanglement","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Gonzalez-Garcia"},{"issue":"1","key":"ref27","first-page":"1","article-title":"IS-GAN: Learning disentangled representation for robust person re-identification","author":"Eom","year":"2021","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383526"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16967"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00806"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref32","first-page":"2610","article-title":"Isolating sources of disentanglement in variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00794"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_13"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref37","first-page":"368","article-title":"The information bottleneck method","volume-title":"Proc. 37th Annu. Allerton Conf. Commun., Control Comput.","author":"Tishby"},{"key":"ref38","article-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv","year":"2017","journal-title":"arXiv:1703.00810"},{"key":"ref39","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Locatello"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"ref45","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3100641"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780272"},{"key":"ref48","article-title":"On the estimation of information measures of continuous distributions","author":"Pichler","year":"2020","journal-title":"arXiv:2002.02851"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089037"},{"key":"ref50","first-page":"1","article-title":"Unsupervised learning via maximizing mutual information in neural population coding","volume-title":"Proc. AAAI Spring Symp.","author":"Huang"},{"key":"ref51","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2914897"},{"key":"ref53","article-title":"Max-MIG: An information theoretic approach for joint learning from crowds","author":"Cao","year":"2019","journal-title":"arXiv:1905.13436"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849720"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/2.36"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.6.1129"},{"key":"ref57","first-page":"1","article-title":"Deep variational information bottleneck","volume-title":"Proc. ICLR","author":"Alemi"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2018.8503149"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007665907178"},{"key":"ref60","first-page":"4402","article-title":"Disentangling disentanglement in variational autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mathieu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00665"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071119"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3105175"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17120"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.673"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00177"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-802806-3.00008-7"},{"key":"ref69","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Vahdat"},{"key":"ref70","first-page":"1692","article-title":"A deep semi-NMF model for learning hidden representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Trigeorgis"},{"key":"ref71","first-page":"1","article-title":"Semi-supervised learning with ladder networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Rasmus"},{"key":"ref72","first-page":"2368","article-title":"Deconstructing the ladder network architecture","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Pezeshki"},{"key":"ref73","first-page":"3738","article-title":"Ladder variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"S\u00f8nderby"},{"key":"ref74","first-page":"1","article-title":"An architecture for deep, hierarchical generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bachman"},{"key":"ref75","article-title":"PixelVAE: A latent variable model for natural images","author":"Gulrajani","year":"2016","journal-title":"arXiv:1611.05013"},{"key":"ref76","first-page":"1","article-title":"Variational autoencoders with jointly optimized latent dependency structure","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"He"},{"key":"ref77","article-title":"Learning hierarchical features from generative models","author":"Zhao","year":"2017","journal-title":"arXiv:1702.08396"},{"key":"ref78","first-page":"2525","article-title":"Structured disentangled representations","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Esmaeili"},{"key":"ref79","first-page":"9084","article-title":"Benchmarks, algorithms, and metrics for hierarchical disentanglement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ross"},{"key":"ref80","first-page":"1","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Razavi"},{"key":"ref81","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016","journal-title":"arXiv:1605.08803"},{"key":"ref82","article-title":"Information bottleneck through variational glasses","author":"Voloshynovskiy","year":"2019","journal-title":"arXiv:1912.00830"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068870"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s10463-011-0343-8"},{"key":"ref85","article-title":"Adversarial autoencoders","author":"Makhzani","year":"2015","journal-title":"arXiv:1511.05644"},{"key":"ref86","volume-title":"The MNIST Database of Handwritten Digits","author":"LeCun","year":"1998"},{"key":"ref87","volume-title":"DSPRITES: Disentanglement testing sprites dataset (2017)","author":"Matthey","year":"2020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref89","first-page":"1","article-title":"Variational inference of disentangled latent concepts from unlabeled observations","volume-title":"Proc. ICLR","author":"Kumar"},{"key":"ref90","first-page":"1","article-title":"Learning deep disentangled embeddings with the F-statistic loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ridgeway"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10623582\/10041431.pdf?arnumber=10041431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T18:15:14Z","timestamp":1722968114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10041431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":90,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3241791","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}