{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:15:32Z","timestamp":1775229332812,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Fund for Distinguished Young Scholars","award":["62025205"],"award-info":[{"award-number":["62025205"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472354"],"award-info":[{"award-number":["62472354"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tmc.2025.3572215","type":"journal-article","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T14:08:54Z","timestamp":1748268534000},"page":"10573-10589","source":"Crossref","is-referenced-by-count":2,"title":["AdaShift: Anti-Collapse and Real-Time Deep Model Evolution for Mobile Vision Applications"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1663-9955","authenticated-orcid":false,"given":"Ke","family":"Ma","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-2467","authenticated-orcid":false,"given":"Bin","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4402-1260","authenticated-orcid":false,"given":"Sicong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8131-6178","authenticated-orcid":false,"given":"Cheng","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2486-2348","authenticated-orcid":false,"given":"Siqi","family":"Luo","sequence":"additional","affiliation":[{"name":"Huawei Cloud, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4342-6015","authenticated-orcid":false,"given":"Zimu","family":"Zheng","sequence":"additional","affiliation":[{"name":"Huawei Cloud, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9905-3238","authenticated-orcid":false,"given":"Zhiwen","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3569464"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3549551"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3448125"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2935384"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217046"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.112"},{"key":"ref9","first-page":"3145","article-title":"Can autonomous vehicles identify, recover from, and adapt to distribution shifts?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Filos"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02315"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00453"},{"key":"ref15","first-page":"1","article-title":"Towards stable test-time adaptation in dynamic wild world","volume-title":"Proc. 2023 Int. Conf. Learn. Representations","author":"Niu"},{"key":"ref16","first-page":"1","article-title":"Entropy is not enough for test-time adaptation: From the perspective of disentangled factors","volume-title":"Proc. 2024 Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2020.3001517"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3195239"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01480"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593862"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02181-w"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699339"},{"key":"ref23","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref24","first-page":"1","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref25","article-title":"SoTTA: Robust test-time adaptation on noisy data streams","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gong"},{"key":"ref26","first-page":"38629","article-title":"MEMO: Test time robustness via adaptation and augmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01859"},{"key":"ref28","article-title":"RDumb: A simple approach that questions our progress in continual test-time adaptation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Press"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.803"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3319952"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699361"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10059-3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00536"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3343448"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2989129"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3421511"},{"key":"ref37","first-page":"12934","article-title":"EfficientFormer: Vision transformers at MobileNet speed","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3223412"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3466931"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796657"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3478073"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123123"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3487294"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3643560"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3446271"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363304"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539263"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3432208"},{"key":"ref49","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Grandvalet"},{"key":"ref50","article-title":"Virtual KITTI 2","author":"Cabon","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3007457"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351424"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1137\/1118101"},{"key":"ref56","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref57","first-page":"1","article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"Proc. 2022 Int. Conf. Learn. Representations","author":"He"},{"key":"ref58","first-page":"16888","article-title":"Efficient test-time model adaptation without forgetting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Niu"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref61","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02068"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082316"},{"key":"ref66","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Schneider"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref69","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref70","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","author":"Hendrycks","year":"2019"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11154819\/11015910.pdf?arnumber=11015910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T19:53:11Z","timestamp":1757533991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11015910\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":68,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3572215","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}