{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:22:17Z","timestamp":1757622137408,"version":"3.44.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100007224","name":"National Research Foundation (NRF) funded by Ministry of Science and ICT (MSIT) of Korean Government","doi-asserted-by":"publisher","award":["2021R1A2C3006659"],"award-info":[{"award-number":["2021R1A2C3006659"]}],"id":[{"id":"10.13039\/100007224","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) funded by MSIT of Korean Government","doi-asserted-by":"publisher","award":["RS-2022-II220953","RS-2021-II211343"],"award-info":[{"award-number":["RS-2022-II220953","RS-2021-II211343"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3602672","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:47:29Z","timestamp":1756154849000},"page":"150473-150488","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating the Bias in the Model for Continual Test-Time Adaptation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7701-6639","authenticated-orcid":false,"given":"Inseop","family":"Chung","sequence":"first","affiliation":[{"name":"Samsung Electronics Company Ltd., Yeongtong-gu, Suwon-si, Gyeonggi-do, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9364-7950","authenticated-orcid":false,"given":"Kyomin","family":"Hwang","sequence":"additional","affiliation":[{"name":"Graduate School of Convergence Science and Technology, Seoul National University, Gwanak, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8461-2260","authenticated-orcid":false,"given":"Jayeon","family":"Yoo","sequence":"additional","affiliation":[{"name":"Graduate School of Convergence Science and Technology, Seoul National University, Gwanak, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1792-0327","authenticated-orcid":false,"given":"Nojun","family":"Kwak","sequence":"additional","affiliation":[{"name":"Graduate School of Convergence Science and Technology, Seoul National University, Gwanak, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks","key":"ref1"},{"key":"ref2","first-page":"5637","article-title":"WILDS: A benchmark of in-the-wild distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Sun","key":"ref3"},{"article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang","key":"ref4"},{"key":"ref5","article-title":"MEMO: Test time robustness via adaptation and augmentation","author":"Zhang","year":"2021","journal-title":"arXiv:2110.09506"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"ref7","article-title":"Efficient test-time model adaptation without forgetting","author":"Niu","year":"2022","journal-title":"arXiv:2204.02610"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"article-title":"Conditional adversarial domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Long","key":"ref11"},{"key":"ref12","first-page":"17543","article-title":"Revisiting realistic test-time training: Sequential inference and adaptation by anchored clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Su"},{"article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref15","article-title":"TTN: A domain-shift aware batch normalization in test-time adaptation","author":"Lim","year":"2023","journal-title":"arXiv:2302.05155"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01005"},{"key":"ref17","article-title":"CAFA: Class-aware feature alignment for test-time adaptation","author":"Jung","year":"2022","journal-title":"arXiv:2206.00205"},{"article-title":"Test-time classifier adjustment module for modelagnostic domain generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Iwasawa","key":"ref18"},{"article-title":"Test-time adaptation via self-training with nearest neighbor information","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Jang","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892154"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00349"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00744"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01147"},{"article-title":"Mecta: Memory-economic continual test-time model adaptation","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Hong","key":"ref24"},{"key":"ref25","article-title":"NOTE: Robust continual test-time adaptation against temporal correlation","author":"Gong","year":"2022","journal-title":"arXiv:2208.05117"},{"key":"ref26","article-title":"Towards stable test-time adaptation in dynamic wild world","author":"Niu","year":"2023","journal-title":"arXiv:2302.12400"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01528"},{"key":"ref28","article-title":"SoTTA: Robust test-time adaptation on noisy data streams","author":"Gong","year":"2023","journal-title":"arXiv:2310.10074"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref29"},{"key":"ref30","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","author":"Hendrycks","year":"2019","journal-title":"arXiv:1912.02781"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref32","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 32","author":"Paszke"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01920"},{"key":"ref34","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref40","article-title":"Unbiased teacher for semi-supervised object detection","author":"Liu","year":"2021","journal-title":"arXiv:2102.09480"},{"key":"ref41","article-title":"A simple semi-supervised learning framework for object detection","author":"Sohn","year":"2020","journal-title":"arXiv:2005.04757"},{"key":"ref42","article-title":"When source-free domain adaptation meets learning with noisy labels","author":"Yi","year":"2023","journal-title":"arXiv:2301.13381"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_26"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02313"},{"article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ganin","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6054"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6123"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00072"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"ref51","article-title":"Adversarial style mining for one-shot unsupervised domain adaptation","author":"Luo","year":"2020","journal-title":"arXiv:2004.06042"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00619"},{"article-title":"Cycle self-training for domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00786"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01134"},{"key":"ref57","article-title":"DELTA: Degradation-free fully test-time adaptation","author":"Zhao","year":"2023","journal-title":"arXiv:2301.13018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01505"},{"key":"ref59","article-title":"Diffusion-TTA: Test-time adaptation of discriminative models via generative feedback","author":"Prabhudesai","year":"2023","journal-title":"arXiv:2311.16102"},{"key":"ref60","article-title":"TEA: Test-time energy adaptation","author":"Yuan","year":"2023","journal-title":"arXiv:2311.14402"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11141419.pdf?arnumber=11141419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:47:13Z","timestamp":1757353633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11141419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3602672","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}