TDG: Text-guided Domain Generalization

TL;DR

This paper introduces TDG, a novel approach that leverages automatically generated domain-relevant text descriptions and prompt learning to improve model generalization to unseen domains, demonstrating superior results on benchmarks.

Contribution

The paper proposes a new text-guided domain generalization framework that integrates generated text features with image features for better unseen domain performance.

Findings

Achieves superior performance on multiple DG benchmarks.

Effectively leverages generated text information for domain generalization.

Provides an easy-to-implement method with improved results.

Abstract

Domain generalization (DG) attempts to generalize a model trained on single or multiple source domains to the unseen target domain. Benefiting from the success of Visual-and-Language Pre-trained models in recent years, we argue that it is crucial for domain generalization by introducing extra text information. In this paper, we develop a novel Text-guided Domain Generalization (TDG) paradigm for domain generalization, which includes three following aspects. Specifically, we first devise an automatic words generation method to extend the description of current domains with novel domain-relevant words. Then, we embed the generated domain information into the text feature space, by the proposed prompt learning-based text feature generation method, which shares a common representation space with the image feature. Finally, we utilize both input image features and generated text features to train a specially designed classifier that generalizes well on unseen target domains, while the image encoder is also updated under the supervision of gradients back propagated from the classifier. Our experimental results show that the techniques incorporated by TDG contribute to the performance in an easy implementation manner. Experimental results on several domain generalization benchmarks show that our proposed framework achieves superior performance by effectively leveraging generated text information in domain generalization.