Author name: Xiao Chen, Jiazhen Huang, Zhiming Liu, Qinting Jiang, Fanding Huang, Jingyan Jiang, Zhi Wang

arXiv:2506.02671v3 Announce Type: replace
Abstract: Deep neural networks often suffer performance degradation upon deployment due to distribution shifts. Continual Test-Time Adaptation (CTTA) aims to address this issue in an unsupervised manner. Howev…