Prompt-based Distribution Alignment for Unsupervised Domain Adaptation

TL;DR

This paper introduces a prompt-based distribution alignment method for unsupervised domain adaptation that leverages domain knowledge and feature tuning to improve the performance of large pre-trained visual-language models across different domains.

Contribution

The paper proposes a novel prompt-based distribution alignment approach with a two-branch prompt-tuning paradigm and feature banks, enhancing domain adaptation for visual-language models.

Findings

Achieves state-of-the-art results on three benchmarks.

Effectively reduces domain discrepancy with feature tuning.

Improves model discrimination through class-related prompt integration.

Abstract

Recently, despite the unprecedented success of large pre-trained visual-language models (VLMs) on a wide range of downstream tasks, the real-world unsupervised domain adaptation (UDA) problem is still not well explored. Therefore, in this paper, we first experimentally demonstrate that the unsupervised-trained VLMs can significantly reduce the distribution discrepancy between source and target domains, thereby improving the performance of UDA. However, a major challenge for directly deploying such models on downstream UDA tasks is prompt engineering, which requires aligning the domain knowledge of source and target domains, since the performance of UDA is severely influenced by a good domain-invariant representation. We further propose a Prompt-based Distribution Alignment (PDA) method to incorporate the domain knowledge into prompt learning. Specifically, PDA employs a two-branch prompt-tuning paradigm, namely base branch and alignment branch. The base branch focuses on integrating class-related representation into prompts, ensuring discrimination among different classes. To further minimize domain discrepancy, for the alignment branch, we construct feature banks for both the source and target domains and propose image-guided feature tuning (IFT) to make the input attend to feature banks, which effectively integrates self-enhanced and cross-domain features into the model. In this way, these two branches can be mutually promoted to enhance the adaptation of VLMs for UDA. We conduct extensive experiments on three benchmarks to demonstrate that our proposed PDA achieves state-of-the-art performance. The code is available at https://github.com/BaiShuanghao/Prompt-based-Distribution-Alignment.