{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T09:33:49Z","timestamp":1761989629334,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"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":["61773316","61871470"],"award-info":[{"award-number":["61773316","61871470"]}],"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":[[2022,11,1]]},"DOI":"10.1109\/tpami.2021.3117908","type":"journal-article","created":{"date-parts":[[2021,10,7]],"date-time":"2021-10-07T03:21:46Z","timestamp":1633576906000},"page":"7551-7562","source":"Crossref","is-referenced-by-count":8,"title":["Gradient Matters: Designing Binarized Neural Networks via Enhanced Information-Flow"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7028-4956","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, Shaanxi, China"}]},{"given":"Nianhui","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, Shaanxi, China"}]},{"given":"Zhitong","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, Shaanxi, China"}]},{"given":"Zeping","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, Shaanxi, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"article-title":"Large scale GAN training for high fidelity natural image synthesis","year":"2018","author":"Brock","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"article-title":"Trained ternary quantization","year":"2016","author":"Zhu","key":"ref7"},{"issue":"1","key":"ref8","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2017","journal-title":"J. Mach. Learn. Res."},{"article-title":"Mixed precision training","year":"2017","author":"Micikevicius","key":"ref9"},{"article-title":"Mixed precision training of convolutional neural networks using integer operations","year":"2018","author":"Das","key":"ref10"},{"key":"ref11","first-page":"3123","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Courbariaux"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1","year":"2016","author":"Courbariaux","key":"ref13"},{"article-title":"WRPN: Wide reduced-precision networks","year":"2017","author":"Mishra","key":"ref14"},{"article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","year":"2013","author":"Bengio","key":"ref15"},{"article-title":"Hypernetworks","year":"2016","author":"Ha","key":"ref16"},{"key":"ref17","first-page":"345","article-title":"Towards accurate binary convolutional neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"article-title":"Training wide residual networks for deployment using a single bit for each weight","year":"2018","author":"McDonnell","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00066"},{"article-title":"BNN+: Improved binary network training","year":"2019","author":"Darabi","key":"ref20"},{"article-title":"Training binary neural networks with real-to-binary convolutions","year":"2020","author":"Martinez","key":"ref21"},{"key":"ref22","first-page":"963","article-title":"Expectation backpropagation: Parameter-free training of multilayer neural networks with continuous or discrete weights","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Soudry"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018344"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00506"},{"article-title":"Categorical reparameterization with gumbel-softmax","year":"2016","author":"Jang","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.598"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461456"},{"article-title":"Self-binarizing networks","year":"2019","author":"Lahoud","key":"ref29"},{"article-title":"SMASH: One-shot model architecture search through hypernetworks","year":"2017","author":"Brock","key":"ref30"},{"article-title":"Graph hypernetworks for neural architecture search","year":"2018","author":"Zhang","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"article-title":"Model compression via distillation and quantization","year":"2018","author":"Polino","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","year":"2016","author":"Zhou","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00280"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00050"},{"article-title":"Neural architecture search with reinforcement learning","year":"2016","author":"Zoph","key":"ref40"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9910240\/09560094.pdf?arnumber=9560094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:16:51Z","timestamp":1705015011000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,1]]},"references-count":40,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3117908","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":[[2022,11,1]]}}}