{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T14:44:11Z","timestamp":1772117051680,"version":"3.50.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"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":["2018B010107001"],"award-info":[{"award-number":["2018B010107001"]}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Laureate Fellowship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/tpami.2021.3088904","type":"journal-article","created":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T20:24:02Z","timestamp":1623702242000},"page":"6140-6152","source":"Crossref","is-referenced-by-count":25,"title":["Effective Training of Convolutional Neural Networks With Low-Bitwidth Weights and Activations"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0074-0303","authenticated-orcid":false,"given":"Bohan","family":"Zhuang","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-756X","authenticated-orcid":false,"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6745-3050","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3584-795X","authenticated-orcid":false,"given":"Lingqiao","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Adelaide, Adelaide, SA, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7790-6423","authenticated-orcid":false,"given":"Ian","family":"Reid","sequence":"additional","affiliation":[{"name":"The University of Adelaide, Adelaide, SA, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8648-8718","authenticated-orcid":false,"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Repren.","author":"Simonyan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"883","article-title":"Discrimination-aware channel pruning for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhuang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref6","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref7","article-title":"Compression of deep convolutional neural networks for fast and low power mobile applications","author":"Kim","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"ref9","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","volume-title":"Proc. Int. Conf. Learn. Repren.","author":"Zhou"},{"key":"ref10","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":"ref11","article-title":"Trained ternary quantization","volume-title":"Proc. Int. Conf. Learn. Repren.","author":"Zhu"},{"key":"ref12","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref14","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"issue":"1","key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref18","article-title":"Fitnets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Repren.","author":"Romero"},{"key":"ref19","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshops","author":"Hinton"},{"key":"ref20","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Repren.","author":"Parisotto"},{"key":"ref21","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Zagoruyko"},{"key":"ref22","first-page":"2654","article-title":"Do deep nets really need to be deep?","volume-title":"Proc. 27th Adv. Neural Inf. Process. Syst.","author":"Ba"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00826"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref25","first-page":"4114","article-title":"Binarized neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hubara"},{"key":"ref26","article-title":"Training competitive binary neural networks from scratch","author":"Bethge","year":"2018"},{"key":"ref27","article-title":"Learning to train a binary neural network","author":"Bethge","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10862"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.430"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref31","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018"},{"key":"ref32","article-title":"Learned step size quantization","volume-title":"Proc. Int. Conf. Learn. Repren.","author":"Esser"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00050"},{"key":"ref34","first-page":"344","article-title":"Towards accurate binary convolutional neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref38","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref39","article-title":"Loss-aware weight quantization of deep networks","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Hou"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01167"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2996936"},{"key":"ref42","article-title":"Proxquant: Quantized neural networks via proximal operators","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Bai"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.761"},{"key":"ref44","article-title":"Model compression via distillation and quantization","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Polino"},{"key":"ref45","article-title":"Relaxed quantization for discretized neural networks","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Louizos"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_19"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3129393"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref50","article-title":"SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size","author":"Iandola","year":"2016"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref52","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Zoph"},{"key":"ref53","first-page":"4095","article-title":"Efficient neural architecture search via parameter sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pham"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref57","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Liu"},{"key":"ref58","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Cai"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref60","article-title":"N2N learning: Network to network compression via policy gradient reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Ashok"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00821"},{"key":"ref63","first-page":"759","article-title":"Network pruning via transformable architecture search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref65","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_17"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00067"},{"key":"ref68","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Mishra"},{"key":"ref69","first-page":"1319","article-title":"Maxout networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goodfellow"},{"key":"ref70","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wan"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.515"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.189"},{"key":"ref73","article-title":"Slimmable neural networks","author":"Yu","year":"2019"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref75","first-page":"1","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-038"},{"key":"ref78","article-title":"Precision highway for ultra low-precision quantization","author":"Park","year":"2018"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9893034\/09454278.pdf?arnumber=9454278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:11:00Z","timestamp":1705014660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9454278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":78,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3088904","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":[[2022,10,1]]}}}