Adapting to Distribution Shift by Visual Domain Prompt Generation

arXiv:2405.02797v1 Announce Type: cross
Abstract: In this paper, we aim to adapt a model at test-time using a few unlabeled data to address distribution shifts. To tackle the challenges of extracting domain knowledge from a limited amount of data, it is crucial to utilize correlated information from pre-trained backbones and source domains. Previous studies fail to utilize recent foundation models with strong out-of-distribution generalization. Additionally, domain-centric designs are not flavored in their works. Furthermore, they employ the process of modelling …

abstract adapt aim arxiv challenges cs.cv cs.lg data distribution domain domain knowledge information knowledge paper prompt shift test type visual