{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:00:02Z","timestamp":1778007602220,"version":"3.51.4"},"reference-count":29,"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":[{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2016R1D1A1B04933156"],"award-info":[{"award-number":["NRF-2016R1D1A1B04933156"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3312572","type":"journal-article","created":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T17:31:38Z","timestamp":1694021498000},"page":"102981-102990","source":"Crossref","is-referenced-by-count":15,"title":["Enabling Large Batch Size Training for DNN Models Beyond the Memory Limit While Maintaining Performance"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7502-4080","authenticated-orcid":false,"given":"Xinyu","family":"Piao","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Korea University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Doangjoo","family":"Synn","sequence":"additional","affiliation":[{"name":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6979-9362","authenticated-orcid":false,"given":"Jooyoung","family":"Park","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1828-7807","authenticated-orcid":false,"given":"Jong-Kook","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref2","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00647"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"ref18","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","author":"cao","year":"2021","journal-title":"arXiv 2105 05537"},{"key":"ref24","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc of USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"key":"ref23","article-title":"Large batch training of convolutional networks","author":"you","year":"2017","journal-title":"arXiv 1708 03888"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3458336.3465289"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","first-page":"1","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref28","first-page":"2279","article-title":"Exploring hidden dimensions in parallelizing convolutional neural networks","author":"jia","year":"2018","journal-title":"Proc ICML"},{"key":"ref27","article-title":"One weird trick for parallelizing convolutional neural networks","author":"krizhevsky","year":"2014","journal-title":"arXiv 1404 5997"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623612"},{"key":"ref8","first-page":"1","article-title":"On model parallelization and scheduling strategies for distributed machine learning","volume":"27","author":"lee","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","first-page":"1","article-title":"Large scale distributed deep networks","volume":"25","author":"dean","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","first-page":"1","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume":"32","author":"huang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","first-page":"2098","article-title":"Decoupled parallel backpropagation with convergence guarantee","author":"huo","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","first-page":"1","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume":"26","author":"ho","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"ref5","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume":"1","author":"jia","year":"2019","journal-title":"Proc Mach Learn Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10242106.pdf?arnumber=10242106","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T18:30:25Z","timestamp":1697481025000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10242106\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3312572","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}