{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T13:43:13Z","timestamp":1779111793576,"version":"3.51.4"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"SmartMore"},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["PRP\/065\/20FX"],"award-info":[{"award-number":["PRP\/065\/20FX"]}],"id":[{"id":"10.13039\/501100010428","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":[[2024,12]]},"DOI":"10.1109\/tnnls.2023.3300309","type":"journal-article","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T18:01:21Z","timestamp":1692813681000},"page":"17164-17176","source":"Crossref","is-referenced-by-count":18,"title":["Quantization via Distillation and Contrastive Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2884-2459","authenticated-orcid":false,"given":"Zehua","family":"Pei","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7994-6290","authenticated-orcid":false,"given":"Xufeng","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9501-9254","authenticated-orcid":false,"given":"Wenqian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-4810","authenticated-orcid":false,"given":"Bei","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref3","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Gehring"},{"key":"ref4","article-title":"Ternary weight networks","author":"Li","year":"2016","journal-title":"arXiv:1605.04711"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.761"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00826"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref9","article-title":"Model compression via distillation and quantization","author":"Polino","year":"2018","journal-title":"arXiv:1802.05668"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref15","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00495"},{"key":"ref17","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018","journal-title":"arXiv:1805.06085"},{"key":"ref18","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume-title":"Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Courbariaux"},{"key":"ref19","article-title":"Ternary neural networks with fine-grained quantization","author":"Mellempudi","year":"2017","journal-title":"arXiv:1705.01462"},{"key":"ref20","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","author":"Zhou","year":"2017","journal-title":"arXiv:1702.03044"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01687-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01540"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2774288"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069886"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref27","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1","author":"Courbariaux","year":"2016","journal-title":"arXiv:1602.02830"},{"key":"ref28","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv:1606.06160"},{"key":"ref29","article-title":"Trained ternary quantization","author":"Zhu","year":"2016","journal-title":"arXiv:1612.01064"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref31","first-page":"112","article-title":"Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks","volume":"2","author":"Jain","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref32","article-title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","author":"Li","year":"2021","journal-title":"arXiv:2102.05426"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01202"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00638"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00522"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00448"},{"key":"ref39","article-title":"Learned step size quantization","author":"Esser","year":"2019","journal-title":"arXiv:1902.08153"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00158"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3223018"},{"key":"ref43","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_40"},{"key":"ref46","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","author":"Mishra","year":"2017","journal-title":"arXiv:1711.05852"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00363"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref49","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref50","article-title":"Learning deep representations by mutual information estimation and maximization","author":"Hjelm","year":"2018","journal-title":"arXiv:1808.06670"},{"key":"ref51","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Henaff"},{"key":"ref52","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3191086"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_35"},{"key":"ref56","first-page":"18518","article-title":"HAWQ-V2: Hessian aware trace-weighted quantization of neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Dong"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/1944345.1944349"},{"key":"ref58","article-title":"Integer quantization for deep learning inference: Principles and empirical evaluation","author":"Wu","year":"2020","journal-title":"arXiv:2004.09602"},{"key":"ref59","article-title":"Additive powers-of-two quantization: An efficient non-uniform discretization for neural networks","author":"Li","year":"2019","journal-title":"arXiv:1909.13144"},{"key":"ref60","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref63","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10772360\/10227741.pdf?arnumber=10227741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T19:08:35Z","timestamp":1733252915000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10227741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":65,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3300309","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}