.png){kind=icon}
.png){kind=icon}
Return
Prototypical class-wise test-time adaptation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2024.10.011.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Test-time adaptation (TTA) refines pre-trained models during deployment, enabling them to effectively manage new, previously unseen data. However, existing TTA methods focus mainly on global domain alignment, which reduces domain-level gaps but often leads to suboptimal performance. This is because they fail to explicitly consider class-wise alignment, resulting in errors when reliable pseudo-labels are unavailable and source domain samples are inaccessible. In this study, we propose a prototypical class-wise test-time adaptation method, which consists of class-wise prototype adaptation and reliable pseudo-labeling. Amain challenge in this approach is the lack of direct access to source domain samples. We leverage the class-specific knowledge contained in the weights of the pre-trained model. To construct class prototypes from the unlabeled target domain, we further introduce a methodology to enhance the reliability of pseudo labels. Our method is adaptable to various models and has been extensively validated, consistently outperforming baselines across multiple benchmark datasets.
Keywords:
Test-time adaptation
Class-wise alignment
Class prototypes
Continual learning
Image classification
Journal
IF:
3.3
Papers:
7.8K
Citations:
1.6W