{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:00Z","timestamp":1740169200641,"version":"3.37.3"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003708","name":"Korea Institute of Science and Technology Information","doi-asserted-by":"publisher","award":["K-20-L04-C01"],"award-info":[{"award-number":["K-20-L04-C01"]}],"id":[{"id":"10.13039\/501100003708","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3038164","type":"journal-article","created":{"date-parts":[[2020,11,16]],"date-time":"2020-11-16T20:52:44Z","timestamp":1605559964000},"page":"207683-207690","source":"Crossref","is-referenced-by-count":3,"title":["Spatial Shift Point-Wise Quantization"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7775-3172","authenticated-orcid":false,"given":"Eunhui","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6929-0825","authenticated-orcid":false,"given":"Kyong-Ha","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2019","author":"feng","journal-title":"Custom-Op","key":"ref33"},{"year":"2016","author":"wu","journal-title":"Tensorpack","key":"ref32"},{"key":"ref31","first-page":"7346","article-title":"Normalization helps training of quantized LSTM","author":"hou","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1007\/978-3-030-58539-6_26"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.5244\/C.30.87"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/CVPR.2018.00951"},{"key":"ref11","first-page":"5951","article-title":"Constructing fast network through deconstruction of convolution","author":"jeon","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR.2019.00741"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref14","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"arXiv 1905 11946"},{"key":"ref15","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 [cs]"},{"key":"ref16","first-page":"3123","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"4107","article-title":"Binarized neural networks","author":"hubara","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref19","article-title":"And the bit goes down: Revisiting the quantization of neural networks","author":"stock","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref28","first-page":"525","article-title":"Xnor-Net: ImageNet classification using binary convolutional neural networks","author":"rastegariy","year":"2016","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","article-title":"DoReFa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"zhou","year":"2016","journal-title":"arXiv 1606 06160 [cs]"},{"key":"ref3","first-page":"18","article-title":"Recent trends in lightweight technology for deep neural networks","volume":"38","author":"kim","year":"2020","journal-title":"KIISE Communication"},{"key":"ref6","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/978-3-030-58610-2_34"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref8","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"year":"2020","author":"research","journal-title":"10 Technological Trends in 2020","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR.2018.00716"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ACCESS.2018.2877890"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref22","article-title":"Loss-aware binarization of deep networks","author":"hou","year":"2016","journal-title":"arXiv 1611 01600"},{"key":"ref21","article-title":"Neural networks for machine learning","volume":"264","author":"hinton","year":"2012","journal-title":"Coursera video lectures"},{"key":"ref24","first-page":"3916","article-title":"Metaquant: Learning to quantize by learning to penetrate non-differentiable quantization","author":"chen","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","article-title":"Loss-aware weight quantization of deep networks","author":"hou","year":"2018","journal-title":"arXiv 1802 08635"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR.2019.00748"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1007\/978-3-030-01267-0_44"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09260175.pdf?arnumber=9260175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:54:59Z","timestamp":1639770899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9260175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3038164","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}