{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:21:29Z","timestamp":1730254889744,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956164","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:34:13Z","timestamp":1669732453000},"page":"1822-1828","source":"Crossref","is-referenced-by-count":1,"title":["ODG-Q: Robust Quantization via Online Domain Generalization"],"prefix":"10.1109","author":[{"given":"Chaofan","family":"Tao","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}]},{"given":"Ngai","family":"Wong","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00031"},{"journal-title":"Adversarial examples in the physical world","year":"2016","author":"kurakin","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"Defensive quantization: When efficiency meets robustness","year":"2019","author":"lin","key":"ref12"},{"article-title":"Rotated binary neural network","year":"2020","author":"lin","key":"ref13"},{"key":"ref14","article-title":"Random mask: Towards robust convolutional neural networks","author":"luo","year":"2020","journal-title":"ICLRE"},{"article-title":"Towards deep learning models resistant to adversarial attacks","year":"2017","author":"madry","key":"ref15"},{"key":"ref16","first-page":"525","article-title":"Xnor-net: Imagenet classification using binary convolutional neural networks","author":"rastegari","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOS1140"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"article-title":"Label smoothing and logit squeezing: a replacement for adversarial training?","year":"2019","author":"shafahi","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Mitigating adversarial effects through randomization","year":"2017","author":"xie","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482272"},{"article-title":"Explaining and harnessing adversarial examples","year":"2014","author":"goodfellow","key":"ref6"},{"key":"ref29","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","author":"zhang","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"article-title":"Online learning: A comprehensive survey","year":"2018","author":"hoi","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018110"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref9"},{"article-title":"Post-training 4-bit quantization of convolution networks for rapid-deployment","year":"2018","author":"banner","key":"ref1"},{"key":"ref20","article-title":"Adversarial training for free!","volume":"32","author":"shafahi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_33"},{"article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","year":"2013","author":"simonyan","key":"ref21"},{"article-title":"Ensemble adversarial training: Attacks and defenses","year":"2017","author":"tram\u00e8r","key":"ref24"},{"article-title":"Fat: Learning low-bitwidth parametric representation via frequency-aware transformation","year":"2021","author":"tao","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref25","article-title":"Visualizing data using t-sne","volume":"9","author":"der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956164.pdf?arnumber=9956164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T15:04:26Z","timestamp":1671462266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956164","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}