{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T11:52:03Z","timestamp":1742385123021,"version":"3.37.3"},"reference-count":44,"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\/501100002460","name":"Chung-Ang University","doi-asserted-by":"publisher","award":["Chung-Ang University Research Scholarship Grants i"],"award-info":[{"award-number":["Chung-Ang University Research Scholarship Grants i"]}],"id":[{"id":"10.13039\/501100002460","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea government","award":["2021-0-01341, AIGS Program (Chung-Ang University)"],"award-info":[{"award-number":["2021-0-01341, AIGS Program (Chung-Ang University)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3339793","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T18:25:42Z","timestamp":1701800742000},"page":"137709-137717","source":"Crossref","is-referenced-by-count":1,"title":["Task-Aware Dynamic Model Optimization for Multi-Task Learning"],"prefix":"10.1109","volume":"11","author":[{"given":"Sujin","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5313-5652","authenticated-orcid":false,"given":"Hyundong","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0840-0044","authenticated-orcid":false,"given":"Eunwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref2","article-title":"A survey of model compression and acceleration for deep neural networks","author":"Cheng","year":"2017","journal-title":"arXiv:1710.09282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01206"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00741"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2139"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00904"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00663"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.06.001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/34.291440"},{"key":"ref17","article-title":"Learning multiple visual domains with residual adapters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Rebuffi"},{"key":"ref18","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671640"},{"key":"ref22","article-title":"Resource-efficient deep learning: A survey on model-, arithmetic-, and implementation-level techniques","author":"Lee","year":"2021","journal-title":"arXiv:2112.15131"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2023.128771"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6424"},{"key":"ref25","first-page":"27503","article-title":"Efficiently identifying task groupings for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Fifty"},{"key":"ref26","article-title":"SVCCA: Singular vector canonical correlation analysis for deep learning dynamics and interpretability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Raghu"},{"key":"ref27","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kornblith"},{"key":"ref28","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016","journal-title":"arXiv:1609.02907"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00991836"},{"key":"ref30","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Han"},{"key":"ref31","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"Frankle","year":"2018","journal-title":"arXiv:1803.03635"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01267"},{"key":"ref33","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.217"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NIPS Workshop Deep Learn. Unsupervised Feature Learn.","author":"Netzer","key":"ref39"},{"key":"ref40","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"arXiv:1212.0402"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10345562.pdf?arnumber=10345562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:47:07Z","timestamp":1705024027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10345562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3339793","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}