{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:17:00Z","timestamp":1776889020946,"version":"3.51.2"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2019B010155002"],"award-info":[{"award-number":["2019B010155002"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2018B010107001"],"award-info":[{"award-number":["2018B010107001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072190"],"award-info":[{"award-number":["62072190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Guangdong Introducing Innovative and Enterpreneurial Teams","award":["2017ZT07X183"],"award-info":[{"award-number":["2017ZT07X183"]}]},{"name":"National Key R&D Program of China","award":["2022ZD0118700"],"award-info":[{"award-number":["2022ZD0118700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3275159","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T17:31:12Z","timestamp":1683826272000},"page":"12459-12473","source":"Crossref","is-referenced-by-count":11,"title":["Single-Path Bit Sharing for Automatic Loss-Aware Model Compression"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6745-3050","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"first","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0074-0303","authenticated-orcid":false,"given":"Bohan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5859-6829","authenticated-orcid":false,"given":"Peng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9444-3763","authenticated-orcid":false,"given":"Jianfei","family":"Cai","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-756X","authenticated-orcid":false,"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref57","first-page":"3288","article-title":"Bayesian compression for deep learning","author":"louizos","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref56","first-page":"1","article-title":"Relaxed quantization for discretized neural networks","author":"louizos","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858232"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_3"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref52","first-page":"28092","article-title":"Post-training quantization for vision transformer","author":"liu","year":"2021","journal-title":"Int Conf Neural Inf Process Syst"},{"key":"ref55","first-page":"1","article-title":"AutoQ: Automated kernel-wise neural network quantization","author":"lou","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref54","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref51","first-page":"1","article-title":"Rethinking the value of network pruning","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","first-page":"6936","article-title":"How do adam and training strategies help BNNs optimization","author":"liu","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00290"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.282"},{"key":"ref48","first-page":"1","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref41","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref44","first-page":"1","article-title":"Additive powers-of-two quantization: An efficient non-uniform discretization for neural networks","author":"li","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","first-page":"1","article-title":"Pruning filters for efficient convnets","author":"li","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2874634"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00530"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref3","first-page":"1","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1109\/TPAMI.2020.3012096","article-title":"Improving generative adversarial networks with local coordinate coding","volume":"44","author":"cao","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00242"},{"key":"ref100","first-page":"1","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref40","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16950"},{"key":"ref37","article-title":"Towards efficient training for neural network quantization","author":"jin","year":"2019"},{"key":"ref36","first-page":"4107","article-title":"Binarized neural networks","author":"hubara","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref39","first-page":"5506","article-title":"I-BERT: Integer-only bert quantization","author":"kim","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref24","first-page":"1379","article-title":"Dynamic network surgery for efficient DNNs","author":"guo","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2908352"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref25","first-page":"735","article-title":"NAT: Neural architecture transformer for accurate and compact architectures","author":"guo","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref20","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00161"},{"key":"ref21","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref28","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"1","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00521"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01167"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","first-page":"18518","article-title":"HAWQ-V2: Hessian aware trace-weighted quantization of neural networks","author":"dong","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref14","first-page":"759","article-title":"Network pruning via transformable architecture search","author":"dong","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00826"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00156"},{"key":"ref11","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"choi","year":"2018"},{"key":"ref99","first-page":"883","article-title":"Discrimination-aware channel pruning for deep neural networks","author":"zhuang","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s101211259"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00050"},{"key":"ref17","first-page":"1","article-title":"Learned step size quantization","author":"esser","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00915"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922108"},{"key":"ref92","first-page":"259","article-title":"Differentiable joint pruning and quantization for hardware efficiency","author":"ying","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref95","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"zhou","year":"2016"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref91","article-title":"A unified framework of DNN weight pruning and weight clustering\/quantization using ADMM","author":"ye","year":"2018"},{"key":"ref90","first-page":"11875","article-title":"HAWQ-V3: Dyadic neural network quantization","author":"yao","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00190"},{"key":"ref86","article-title":"Mixed precision quantization of convnets via differentiable neural architecture search","author":"wu","year":"2018"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00225"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_1"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00215"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref84","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00524"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref79","first-page":"5741","article-title":"Bayesian bits: Unifying quantization and pruning","author":"van baalen","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref78","first-page":"1","article-title":"Mixed precision DNNs: All you need is a good parametrization","author":"uhlich","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2971421"},{"key":"ref74","first-page":"481","article-title":"Single-path NAS: Designing hardware-efficient convnets in less than 4 hours","author":"stamoulis","year":"2019","journal-title":"Proc Eur Conf Mach Learn Princ Pract Knowl Discov Databases"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00821"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"ref1","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref73","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"ref63","first-page":"1","article-title":"BiBERT: Accurate fully binarized bert","author":"qin","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref65","first-page":"1","article-title":"Distribution-sensitive information retention for accurate binary neural network","volume":"131","author":"qin","year":"2022","journal-title":"Int J Comput Vis"},{"key":"ref60","first-page":"543","article-title":"A method for solving the convex programming problem with convergence rate o (1\/k?2303 2)","volume":"269","author":"nesterov","year":"1983","journal-title":"Proc USSR Acad Sci"},{"key":"ref62","first-page":"4092","article-title":"Efficient neural architecture search via parameter sharing","author":"pham","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref61","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10122994.pdf?arnumber=10122994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:11:04Z","timestamp":1717693864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10122994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":100,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3275159","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}