{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T02:41:55Z","timestamp":1774320115120,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"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":["2019B010155003"],"award-info":[{"award-number":["2019B010155003"]}]},{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["JCYJ20200109114835623"],"award-info":[{"award-number":["JCYJ20200109114835623"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1713203"],"award-info":[{"award-number":["U1713203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Scientific Instrument Developing Project of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["YJKYYQ20190028"],"award-info":[{"award-number":["YJKYYQ20190028"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/tnnls.2021.3064293","type":"journal-article","created":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T22:05:56Z","timestamp":1618437956000},"page":"4960-4970","source":"Crossref","is-referenced-by-count":21,"title":["Deep Network Quantization via Error Compensation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5168-1518","authenticated-orcid":false,"given":"Hanyu","family":"Peng","sequence":"first","affiliation":[{"name":"Multimedia Laboratory, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9132-5625","authenticated-orcid":false,"given":"Jiaxiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3463-0505","authenticated-orcid":false,"given":"Zhiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Multimedia Laboratory, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0677-7358","authenticated-orcid":false,"given":"Shifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Multimedia Laboratory, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8819-8829","authenticated-orcid":false,"given":"Hai-Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref2","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref4","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018","journal-title":"arXiv:1805.06085"},{"key":"ref5","article-title":"Towards the limit of network quantization","author":"Choi","year":"2016","journal-title":"arXiv:1612.01543"},{"key":"ref6","first-page":"7675","article-title":"Training deep neural networks with 8-bit floating point numbers","author":"Wang","year":"2018","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01166"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref10","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00495"},{"key":"ref12","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gupta"},{"key":"ref13","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref18","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"arXiv:1503.02531"},{"key":"ref19","article-title":"Loss-aware weight quantization of deep networks","author":"Hou","year":"2018","journal-title":"arXiv:1802.08635"},{"key":"ref20","article-title":"Loss-aware binarization of deep networks","author":"Hou","year":"2016","journal-title":"arXiv:1611.01600"},{"key":"ref21","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref23","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size","author":"Iandola","year":"2016","journal-title":"arXiv:1602.07360"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref26","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref28","article-title":"Ternary weight networks","author":"Li","year":"2016","journal-title":"arXiv:1605.04711"},{"key":"ref29","first-page":"5811","article-title":"Training quantized nets: A deeper understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref30","first-page":"1","article-title":"Additive powers-of-two quantization: An efficient non-uniform discretization for neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.282"},{"key":"ref32","volume-title":"Fixed point neural network based on floating point neural network quantization","author":"Lin","year":"2019"},{"key":"ref33","first-page":"2181","article-title":"Runtime neural pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref34","first-page":"345","article-title":"Towards accurate binary convolutional neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref35","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"Lin","year":"2017","journal-title":"arXiv:1712.01887"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref37","article-title":"Relaxed quantization for discretized neural networks","author":"Louizos","year":"2018","journal-title":"arXiv:1810.01875"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref40","article-title":"Convolutional neural networks using logarithmic data representation","author":"Miyashita","year":"2016","journal-title":"arXiv:1603.01025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.03.026"},{"key":"ref42","first-page":"5113","article-title":"Collaborative channel pruning for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2418224"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref45","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref46","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/DI9\u20131628"},{"key":"ref48","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref49","first-page":"3123","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","author":"Courbariaux","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00137"},{"key":"ref52","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","author":"Ye","year":"2018","journal-title":"arXiv:1802.00124"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.15"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/448"},{"key":"ref57","first-page":"7543","article-title":"Improving neural network quantization without retraining using outlier channel splitting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref58","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","author":"Zhou","year":"2017","journal-title":"arXiv:1702.03044"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00982"},{"key":"ref60","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv:1606.06160"},{"key":"ref61","article-title":"Trained ternary quantization","author":"Zhu","year":"2016","journal-title":"arXiv:1612.01064"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9872163\/09404314.pdf?arnumber=9404314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:00:15Z","timestamp":1704844815000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9404314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":61,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3064293","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}