arXiv:2407.09498v1 Announce Type: new
Abstract: While Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training phase or modify model parameters at test time through entropy minimization. The former often overlooks unlabeled target data, while the latter doesn’t fully address domain shifts. In this work, our approach, Optimal Transport-guided Test-Time Visual Prompting (OT-VP), handles these problems by leveraging prompt learning at test time to align the target and source domains without accessing the training process or altering pre-trained model parameters. This method involves learning a universal visual prompt for the target domain by optimizing the Optimal Transport distance. With just four prompt tokens learned, OT-VP achieves a $5.0%$ and $1.5%$ increase in averaged accuracy across single-source and multi-source settings on three benchmark datasets, which is $1.2times$ and $1.5times$ the improvement of the state-of-the-art method, respectively.
Source link
lol
