{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:52:10Z","timestamp":1762325530032,"version":"3.37.3"},"reference-count":63,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202396"],"award-info":[{"award-number":["62202396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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.2023.3241945","type":"journal-article","created":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T23:04:28Z","timestamp":1676934268000},"page":"10519-10534","source":"Crossref","is-referenced-by-count":3,"title":["Variational Nested Dropout"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9663-0079","authenticated-orcid":false,"given":"Yufei","family":"Cui","sequence":"first","affiliation":[{"name":"School of Computer Science, McGill University, Montreal, QC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9724-2510","authenticated-orcid":false,"given":"Ziquan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4579-4268","authenticated-orcid":false,"given":"Qiao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2886-2513","authenticated-orcid":false,"given":"Antoni B.","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5252-3442","authenticated-orcid":false,"given":"Xue","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, McGill University, Montreal, QC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tei-Wei","family":"Kuo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei City, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6431-9868","authenticated-orcid":false,"given":"Chun Jason","family":"Xue","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.487"},{"article-title":"Ordering dimensions with nested dropout normalizing flows","year":"2020","author":"Bekasov","key":"ref3"},{"article-title":"The Cramer distance as a solution to biased Wasserstein gradients","year":"2017","author":"Bellemare","key":"ref4"},{"key":"ref5","first-page":"1613","article-title":"Weight uncertainty in neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blundell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_29"},{"article-title":"Once-for-all: Train one network and specialize it for efficient deployment","year":"2019","author":"Cai","key":"ref7"},{"key":"ref8","first-page":"1045","article-title":"Very deep VAEs generalize autoregressive models and can outperform them on images","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Child"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-013-9622-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00242"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/288"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3042525"},{"key":"ref13","first-page":"708","article-title":"Learning disentangled joint continuous and discrete representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dupont"},{"article-title":"Learning compact convolutional neural networks with nested dropout","year":"2014","author":"Finn","key":"ref14"},{"article-title":"Uncertainty in deep learning","year":"2016","author":"Gal","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref17","first-page":"3581","article-title":"Concrete dropout","volume-title":"Proc. Inr. Conf. Neural Inf. Process. Syst.","author":"Gal"},{"key":"ref18","volume-title":"Statistical Theory of Extreme Values and Some Practical Applications: A Series of Lectures","volume":"33","author":"Gumbel","year":"1948"},{"article-title":"On calibration of modern neural networks","year":"2017","author":"Guo","key":"ref19"},{"article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","year":"2015","author":"Han","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","year":"2016","author":"Hendrycks","key":"ref22"},{"key":"ref23","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref24","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins","year":"2017"},{"article-title":"Categorical reparameterization with Gumbel-Softmax","year":"2016","author":"Jang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/c.31.57"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/ISITA.2018.8664326"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00904"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref29"},{"key":"ref30","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref31"},{"key":"ref32","first-page":"6965","article-title":"A probabilistic U-Net for segmentation of ambiguous images","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kohl"},{"article-title":"Sliced-Wasserstein autoencoder: An embarrassingly simple generative model","year":"2018","author":"Kolouri","key":"ref33"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref34"},{"key":"ref35","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lakshminarayanan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref37","first-page":"3288","article-title":"Bayesian compression for deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Louizos"},{"article-title":"Multiplicative normalizing flows for variational Bayesian neural networks","year":"2017","author":"Louizos","key":"ref38"},{"article-title":"Learning sparse neural networks through l_0 regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Louizos","key":"ref39"},{"article-title":"The concrete distribution: A continuous relaxation of discrete random variables","year":"2016","author":"Maddison","key":"ref40"},{"key":"ref41","first-page":"3086","article-title":"A* sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Maddison"},{"article-title":"Variational dropout sparsifies deep neural networks","year":"2017","author":"Molchanov","key":"ref42"},{"volume-title":"Machine Learning: A Probabilistic Perspective","year":"2012","author":"Murphy","key":"ref43"},{"article-title":"Parallel training of DNNs with natural gradient and parameter averaging","year":"2014","author":"Povey","key":"ref44"},{"key":"ref45","first-page":"3222","article-title":"Large-scale Bayesian multi-label learning via topic-based label embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rai"},{"article-title":"Preventing posterior collapse with delta-VAEs","year":"2019","author":"Razavi","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304076"},{"key":"ref48","first-page":"1746","article-title":"Learning ordered representations with nested dropout","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rippel"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273596"},{"key":"ref51","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans"},{"article-title":"Improving GANs using optimal transport","year":"2018","author":"Salimans","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref54"},{"issue":"1","key":"ref55","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jspi.2013.03.018"},{"article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","year":"2019","author":"Tan","key":"ref57"},{"article-title":"Wasserstein auto-encoders","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Tolstikhin","key":"ref58"},{"issue":"12","key":"ref59","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3427617"},{"article-title":"DeepHoyer: Learning sparser neural network with differentiable scale-invariant sparsity measures","year":"2019","author":"Yang","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"article-title":"Slimmable neural networks","year":"2018","author":"Yu","key":"ref64"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10169863\/10049079.pdf?arnumber=10049079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T05:01:24Z","timestamp":1720587684000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10049079\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":63,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3241945","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]]}}}