CADG: A Model Based on Cross Attention for Domain Generalization

TL;DR

This paper introduces CADG, a cross attention-based model that enhances domain generalization by aligning features across different distributions, achieving state-of-the-art results on multiple benchmarks.

Contribution

The paper proposes a novel cross attention mechanism for domain generalization, improving classifier robustness across unseen domains.

Findings

Achieves state-of-the-art performance on domain generalization benchmarks.

Outperforms some ensemble-based methods with a single model.

Effectively aligns features from diverse source domains.

Abstract

In Domain Generalization (DG) tasks, models are trained by using only training data from the source domains to achieve generalization on an unseen target domain, this will suffer from the distribution shift problem. So it's important to learn a classifier to focus on the common representation which can be used to classify on multi-domains, so that this classifier can achieve a high performance on an unseen target domain as well. With the success of cross attention in various cross-modal tasks, we find that cross attention is a powerful mechanism to align the features come from different distributions. So we design a model named CADG (cross attention for domain generalization), wherein cross attention plays a important role, to address distribution shift problem. Such design makes the classifier can be adopted on multi-domains, so the classifier will generalize well on an unseen domain. Experiments show that our proposed method achieves state-of-the-art performance on a variety of domain generalization benchmarks compared with other single model and can even achieve a better performance than some ensemble-based methods.