{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T09:09:08Z","timestamp":1743844148847,"version":"3.37.3"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Key Research and Development Program of Zhejiang Province","award":["2021C01105"],"award-info":[{"award-number":["2021C01105"]}]},{"DOI":"10.13039\/501100015956","name":"Special Project for Research and Development in Key areas of Guangdong Province","doi-asserted-by":"publisher","award":["2020B0101090003"],"award-info":[{"award-number":["2020B0101090003"]}],"id":[{"id":"10.13039\/501100015956","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB2701100"],"award-info":[{"award-number":["2021YFB2701100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3273952","type":"journal-article","created":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T18:58:02Z","timestamp":1683572282000},"page":"46441-46453","source":"Crossref","is-referenced-by-count":4,"title":["Deep Generative Knowledge Distillation by Likelihood Finetuning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5646-1514","authenticated-orcid":false,"given":"Jingru","family":"Li","sequence":"first","affiliation":[{"name":"EAGLE Laboratory, Zhejiang University, Hangzhou, China"}]},{"given":"Xiaofeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Hangzhou Qulian Technology Company Ltd., Hangzhou, China"}]},{"given":"Peiyu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Hangzhou Qulian Technology Company Ltd., Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4629-8845","authenticated-orcid":false,"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Blockchain Research Center, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8608-5628","authenticated-orcid":false,"given":"Zhi","family":"Yu","sequence":"additional","affiliation":[{"name":"EAGLE Laboratory, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00636"},{"key":"ref57","volume":"10","author":"liu","year":"2001","journal-title":"Monte Carlo Strategies in Scientific Computing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref56","article-title":"Variational inference of disentangled latent concepts from unlabeled observations","author":"kumar","year":"2017","journal-title":"arXiv 1711 00848"},{"key":"ref15","article-title":"Improved training of Wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"arXiv 1704 00028"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492900002804"},{"key":"ref14","article-title":"Contrastive model inversion for data-free knowledge distillation","author":"fang","year":"2021","journal-title":"arXiv 2105 08584"},{"journal-title":"Monte Carlo Methods","year":"2013","author":"hammersley","key":"ref58"},{"key":"ref53","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref52","article-title":"Residual energy-based models for text generation","author":"deng","year":"2020","journal-title":"arXiv 2004 11714"},{"key":"ref11","article-title":"Dream distillation: A data-independent model compression framework","author":"bhardwaj","year":"2019","journal-title":"arXiv 1905 07072"},{"key":"ref55","article-title":"Understanding disentangling in SS -VAE","author":"burgess","year":"2018","journal-title":"arXiv 1804 03599"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref54","first-page":"1","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"2015","journal-title":"Proc NIPS"},{"article-title":"Generative adversarial networks","year":"2014","author":"goodfellow","key":"ref17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00390"},{"key":"ref19","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","first-page":"182","article-title":"Regularizing model-based planning with energy-based models","author":"boney","year":"2020","journal-title":"Proc Conf Robot Learn"},{"key":"ref50","article-title":"Your classifier is secretly an energy based model and you should treat it like one","author":"grathwohl","year":"2019","journal-title":"arXiv 1912 03263"},{"key":"ref46","first-page":"10675","article-title":"Zero-shot knowledge distillation from a decision-based black-box model","author":"wang","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3066513"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00368"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref41","article-title":"Paraphrasing complex network: Network compression via factor transfer","author":"kim","year":"2018","journal-title":"arXiv 1802 04977"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20556"},{"key":"ref8","article-title":"Large-scale generative data-free distillation","author":"luo","year":"2020","journal-title":"arXiv 2012 05578"},{"key":"ref7","first-page":"4743","article-title":"Zero-shot knowledge distillation in deep networks","author":"nayak","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","article-title":"Data-free model extraction","author":"truong","year":"2020","journal-title":"arXiv 2011 14779"},{"key":"ref4","article-title":"FitNets: Hints for thin deep nets","author":"romero","year":"2014","journal-title":"arXiv 1412 6550"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01603"},{"key":"ref6","article-title":"Generative models for effective ML on private, decentralized datasets","author":"augenstein","year":"2019","journal-title":"arXiv 1911 06679"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.10.020"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"huang","year":"2017","journal-title":"arXiv 1707 01219"},{"key":"ref80","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00297"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref79"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref78","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"arXiv 1912 01703"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref31","article-title":"Score-based generative modeling through stochastic differential equations","author":"song","year":"2020","journal-title":"arXiv 2011 13456"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref30","first-page":"574","article-title":"Sliced score matching: A scalable approach to density and score estimation","author":"song","year":"2019","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref74","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"welling","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref33","first-page":"1607","article-title":"Born again neural networks","author":"furlanello","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref77","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref76","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2016","journal-title":"arXiv 1612 03928"},{"key":"ref1","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref71","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref70","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref73","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","author":"heusel","year":"2017","journal-title":"Proc NIPS"},{"key":"ref72","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"arXiv 1606 03498"},{"key":"ref24","article-title":"Improved contrastive divergence training of energy based models","author":"du","year":"2020","journal-title":"arXiv 2012 01316"},{"key":"ref68","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2016","journal-title":"arXiv 1511 06434"},{"key":"ref23","article-title":"Learning non-convergent non-persistent short-run MCMC toward energy-based model","author":"nijkamp","year":"2019","journal-title":"arXiv 1904 09770"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00643"},{"key":"ref26","article-title":"Improved denoising diffusion probabilistic models","author":"nichol","year":"2021","journal-title":"arXiv 2102 09672"},{"key":"ref25","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"arXiv 2006 11239"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref20","article-title":"Glow: Generative flow with invertible 1×1 convolutions","author":"kingma","year":"2018","journal-title":"arXiv 1807 03039"},{"key":"ref64","article-title":"Learning energy-based models by diffusion recovery likelihood","author":"gao","year":"2020","journal-title":"arXiv 2012 08125"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00800"},{"key":"ref22","article-title":"Implicit generation and generalization in energy-based models","author":"du","year":"2019","journal-title":"arXiv 1903 08689"},{"article-title":"Inceptionism: Going deeper into neural networks","year":"2015","author":"mordvintsev","key":"ref66"},{"key":"ref21","article-title":"A tutorial on energy-based learning","volume":"1","author":"lecun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref65","article-title":"Generative models as a data source for multiview representation learning","author":"jahanian","year":"2021","journal-title":"arXiv 2106 05258"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref27","article-title":"Elucidating the design space of diffusion-based generative models","author":"karras","year":"2022","journal-title":"arXiv 2206 00364"},{"key":"ref29","article-title":"Denoising diffusion implicit models","author":"song","year":"2020","journal-title":"arXiv 2010 02502"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2009.00736.x"},{"key":"ref62","first-page":"3957","article-title":"Cooperative training of fast thinking initializer and slow thinking solver for conditional learning","volume":"44","author":"xie","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref61","first-page":"11287","article-title":"Score-based generative modeling in latent space","author":"vahdat","year":"2021","journal-title":"Proc Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10121015.pdf?arnumber=10121015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:26:29Z","timestamp":1686594389000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10121015\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3273952","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}