{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:16:14Z","timestamp":1758269774753,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institution of Information and Communications Technology Planning and Evaluation"},{"name":"Korean Government","award":["2021-0-00105","2021-0-00106"],"award-info":[{"award-number":["2021-0-00105","2021-0-00106"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3311027","type":"journal-article","created":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T17:32:00Z","timestamp":1693589520000},"page":"95467-95480","source":"Crossref","is-referenced-by-count":2,"title":["O-2A: Outlier-Aware Compression for 8-bit Post-Training Quantization Model"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3470-835X","authenticated-orcid":false,"given":"Nguyen-Dong","family":"Ho","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Kyung Hee University, Yongin, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8871-8695","authenticated-orcid":false,"given":"Ik-Joon","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Kyung Hee University, Yongin, South Korea"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.01.060"},{"key":"ref57","first-page":"1","article-title":"QDrop: Randomly dropping quantization for extremely low-bit post-training quantization","author":"wei","year":"2022","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14349-6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"ref59","first-page":"1","article-title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","author":"li","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14675-9"},{"key":"ref58","first-page":"1","article-title":"Up or down? Adaptive rounding for post-training quantization","author":"nagel","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref53","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref52","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3057719"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000921"},{"key":"ref54","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2886773"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3258413"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3271749"},{"key":"ref18","first-page":"1","article-title":"An improved iterated greedy algorithm for the distributed hybrid flowshop scheduling problem","author":"lu","year":"2023","journal-title":"Engineering Optimization"},{"key":"ref51","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref46","article-title":"Improving neural network quantization without retraining using outlier channel splitting","author":"zhao","year":"2019","journal-title":"arXiv 1901 09504"},{"key":"ref45","first-page":"4466","article-title":"Accurate post training quantization with small calibration sets","volume":"139","author":"hubara","year":"2021","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317783"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_5"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02340"},{"key":"ref41","first-page":"1","article-title":"Post training 4-bit quantization of convolutional networks for rapid-deployment","author":"banner","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref43","article-title":"A white paper on neural network quantization","author":"nagel","year":"2021","journal-title":"arXiv 2106 08295"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CJECE.2013.6704691"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04566-2"},{"key":"ref7","first-page":"3492","article-title":"Mirror detection with the visual chirality cue","volume":"45","author":"tan","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-04958-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121062"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3107035"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.12.096"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3190366"},{"key":"ref40","first-page":"1","article-title":"Towards accurate post-training network quantization via bit-split and stitching","author":"wang","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref35","first-page":"1","article-title":"Binarized neural networks","volume":"29","author":"hubara","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3289185"},{"key":"ref37","article-title":"Joint training of low-precision neural network with quantization interval parameters","author":"jung","year":"2018","journal-title":"arXiv 1808 05775"},{"key":"ref36","first-page":"1","article-title":"PACT: Parameterized clipping activation for quantized neural networks","author":"choi","year":"2018","journal-title":"Proc ICLR"},{"journal-title":"NVIDIA DGX A100 System Architecture","year":"2020","author":"corporation","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM19573.2019.8993662"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3147032"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3180725"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218594"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17054"},{"key":"ref24","first-page":"1","article-title":"Ten lessons from three generations shaped Google’s TPUv4i: Industrial product","author":"jouppi","year":"2021","journal-title":"Proc ACM\/IEEE 48th Annu Int Symp Comput Archit (ISCA)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref26","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"elsken","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3270519"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3124750"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105860"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11424-022-1030-y"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-03121-8"},{"key":"ref29","first-page":"1","article-title":"Dynamic channel pruning: Feature boosting and suppression","author":"gao","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref60","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10237192.pdf?arnumber=10237192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:12:34Z","timestamp":1696270354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10237192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3311027","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}