{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T14:10:41Z","timestamp":1780582241509,"version":"3.54.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["JP24K02942"],"award-info":[{"award-number":["JP24K02942"]}]},{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["JP23K21676"],"award-info":[{"award-number":["JP23K21676"]}]},{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["JP23K11141"],"award-info":[{"award-number":["JP23K11141"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3608661","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:46:44Z","timestamp":1758563204000},"page":"6110-6125","source":"Crossref","is-referenced-by-count":1,"title":["Exponential Dissimilarity-Dispersion Family for Domain-Specific Representation Learning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4474-3995","authenticated-orcid":false,"given":"Ren","family":"Togo","sequence":"first","affiliation":[{"name":"Faculty of Information Science and Technology, Hokkaido University, Sapporo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9260-0828","authenticated-orcid":false,"given":"Nao","family":"Nakagawa","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5332-8112","authenticated-orcid":false,"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Hokkaido University, Sapporo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1496-1761","authenticated-orcid":false,"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Technology, Hokkaido University, Sapporo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref2","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rezende"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref5","first-page":"2455","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS)","author":"Ha"},{"key":"ref6","first-page":"1480","article-title":"DARLA: Improving zero-shot transfer in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Higgins"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00720"},{"key":"ref8","first-page":"14222","article-title":"Are disentangled representations helpful for abstract visual reasoning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Van Steenkiste"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.107166","article-title":"Discovering influential factors in variational autoencoders","volume":"100","author":"Liu","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539291"},{"key":"ref11","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"Proc. 33rd Int. Conf. Mach. Learn","volume":"48","author":"Larsen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.03.013"},{"key":"ref13","first-page":"1","article-title":"Importance weighted autoencoders","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Burda"},{"key":"ref14","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS)","volume":"29","author":"Kingma"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0056-x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1090\/s0273-0979-09-01249-x"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00794"},{"key":"ref18","first-page":"1","article-title":"Generalized ELBO with constrained optimization, GECO","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS) Workshop Bayesian Deep Learn","author":"Rezende"},{"key":"ref19","article-title":"Balancing reconstruction quality and regularisation in ELBO for VAEs","author":"Lin","year":"2019","journal-title":"arXiv:1909.03765"},{"key":"ref20","first-page":"9179","article-title":"Simple and effective VAE training with calibrated decoders","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rybkin"},{"key":"ref21","first-page":"1","article-title":"SS -VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Higgins"},{"key":"ref22","first-page":"159","article-title":"Fixing a broken ELBO","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Alemi"},{"key":"ref23","first-page":"1","article-title":"Diagnosing and enhancing VAE models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dai"},{"key":"ref24","first-page":"1","article-title":"Understanding disentangling in SS -VAE","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS) Workshop","author":"Burgess"},{"key":"ref25","first-page":"240","article-title":"Cyclical annealing schedule: A simple approach to mitigating KL vanishing","volume-title":"Proc. Conf. North American Chapter Assoc. Comput. Linguistics, Human Lang. Technol","author":"Fu"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.neucom.2022.08.067","article-title":"Preventing oversmoothing in VAE via generalized variance parameterization","volume":"509","author":"Takida","year":"2022","journal-title":"Neurocomputing"},{"key":"ref27","first-page":"9408","article-title":"Don\u2019t blame the ELBO! A linear VAE perspective on posterior collapse","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lucas"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78389-0_24"},{"issue":"233","key":"ref29","first-page":"1","article-title":"A generalised linear model framework for SS -variational autoencoders based on exponential dispersion families","volume":"22","author":"Sicks","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2092435"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2109730"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2012.6467149"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2293423"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2346028"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351172"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2017.11.001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1167\/16.12.326"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2604042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00194"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref46","article-title":"Beta-VAE reproducibility: Challenges and extensions","author":"Fil","year":"2021","journal-title":"arXiv:2112.14278"},{"key":"ref47","first-page":"1","article-title":"Gromov\u2013Wasserstein autoencoders","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Nakagawa"},{"key":"ref48","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Locatello"},{"key":"ref49","first-page":"1","article-title":"Unsupervised model selection for variational disentangled representation learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Duan"},{"key":"ref50","first-page":"12638","article-title":"Joint contrastive learning with infinite possibilities","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Cai"},{"key":"ref51","first-page":"18008","article-title":"Cooperation in the latent space: The benefits of adding mixture components in variational autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Kviman"},{"key":"ref52","first-page":"20950","article-title":"Variational open-domain question answering","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li\u00e9vin"},{"key":"ref53","first-page":"1736","article-title":"Catch missing details: Image reconstruction with frequency augmented variational autoencoder","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit","author":"Lin"},{"key":"ref54","first-page":"368","article-title":"The information bottleneck method","volume-title":"Proc. Annu. Allerton Conf. Commun., Control Comput","author":"Tishby"},{"key":"ref55","first-page":"1","article-title":"Recent advances in autoencoder-based representation learning","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS) Workshop Bayesian Deep Learn","author":"Tschannen"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533671"},{"key":"ref57","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Krizhevsky"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-4-431-55978-8"},{"key":"ref59","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NIPS Workshop Deep Learn. Unsupervised Feature Learn","author":"Netzer"},{"key":"ref60","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Paszke"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref64","article-title":"Learning multiple layers of features from tiny images","volume-title":"M.S. thesis, University of Toronto","author":"Krizhevsky","year":"2009"},{"key":"ref65","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Heusel"},{"key":"ref66","first-page":"1","article-title":"Demystifying MMD GANs","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Bi\u0144kowski"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4206741"},{"key":"ref68","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref69","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00437"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2124295.2124371"},{"key":"ref72","article-title":"Epsilon-VAE: Denoising as visual decoding","author":"Zhao","year":"2024","journal-title":"arXiv:2410.04081"},{"key":"ref73","article-title":"Enhancing variational autoencoders with smooth robust latent encoding","author":"Lee","year":"2025","journal-title":"arXiv:2504.17219"},{"key":"ref74","first-page":"52","article-title":"IntroVAE: Introspective variational autoencoders for photographic image synthesis","volume-title":"Proc. NIPS","author":"Huang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"issue":"1","key":"ref76","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/S0045-7906(01)00011-8","article-title":"The Haar wavelet transform: Its status and achievements","volume":"29","author":"Stankovi\u0107","year":"2003","journal-title":"Comput. Electr. Eng."},{"key":"ref77","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learning Represent. (ICLR)","author":"Simonyan"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref80","first-page":"1","article-title":"EQ-VAE: Equivariance regularized latent space for improved generative image modeling","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Kouzelis"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11175279.pdf?arnumber=11175279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:16:58Z","timestamp":1759238218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11175279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3608661","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}