{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:56:54Z","timestamp":1777888614204,"version":"3.51.4"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02032","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21885-21894","source":"Crossref","is-referenced-by-count":0,"title":["MSQ: Memory-Efficient Bit Sparsification Quantization"],"prefix":"10.1109","author":[{"given":"Seokho","family":"Han","sequence":"first","affiliation":[{"name":"Sungkyunkwan University,Department of Electrical and Computer Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seoyeon","family":"Yoon","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University,Department of Electrical and Computer Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhee","family":"Kim","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University,Department of Electrical and Computer Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongwei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Arizona,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang Eun","family":"Jeon","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University,Department of Electrical and Computer Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanrui","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Arizona,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong Hwan","family":"Ko","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University,Department of Electrical and Computer Engineering,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Post training 4-bit quantization of convolutional networks for rapiddeployment","volume":"32","author":"Banner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3066883"},{"key":"ref3","article-title":"Pact: Parameterized clipping activation for quantized neural networks","author":"Choi","year":"2018","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref6","first-page":"1851818529","article-title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks","volume":"33","author":"Dong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Learned step size quantization","author":"Esser","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Squant: On-the-fly data-free quantization via diagonal hessian approximation","author":"Guo","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref13","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2496"},{"key":"ref15","first-page":"21813","article-title":"Oscillation-free quantization for low-bit vision transformers","volume-title":"In International Conference on Machine Learning","author":"Liu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01946"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref18","first-page":"7197","article-title":"Up or down? adaptive rounding for post-training quantization","volume-title":"In International conference on machine learning","author":"Nagel"},{"key":"ref19","article-title":"Mix-qvit: Mixedprecision vision transformer quantization driven by layer importance and quantization sensitivity","author":"Savakis","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref21","first-page":"11380","article-title":"Winning the lottery with continuous sparsification","volume":"33","author":"Savarese","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"In International conference on machine learning","author":"Touvron"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref25","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"In International Conference on Machine Learning","author":"Xiao"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247982"},{"key":"ref27","article-title":"Bsq: Exploring bit-level sparsity for mixed-precision neural network quantization","author":"Yang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00748"},{"key":"ref29","first-page":"11875","article-title":"Hawq-v3: Dyadic neural network quantization","volume-title":"In International Conference on Machine Learning","author":"Yao"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref31","article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444652.pdf?arnumber=11444652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:26Z","timestamp":1777611206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444652\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02032","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}