Towards Domain-Specific Features Disentanglement for Domain Generalization

TL;DR

This paper introduces CDDG, a contrastive-based disentanglement method that improves domain generalization by effectively separating domain-specific and category features, leading to better cross-domain performance.

Contribution

The paper proposes a novel disentanglement approach that leverages contrastive learning to decouple mutually exclusive features for enhanced domain generalization.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effectively disentangles domain-specific and category features

Visualization confirms successful feature separation

Abstract

Distributional shift between domains poses great challenges to modern machine learning algorithms. The domain generalization (DG) signifies a popular line targeting this issue, where these methods intend to uncover universal patterns across disparate distributions. Noted, the crucial challenge behind DG is the existence of irrelevant domain features, and most prior works overlook this information. Motivated by this, we propose a novel contrastive-based disentanglement method CDDG, to effectively utilize the disentangled features to exploit the over-looked domain-specific features, and thus facilitating the extraction of the desired cross-domain category features for DG tasks. Specifically, CDDG learns to decouple inherent mutually exclusive features by leveraging them in the latent space, thus making the learning discriminative. Extensive experiments conducted on various benchmark datasets demonstrate the superiority of our method compared to other state-of-the-art approaches. Furthermore, visualization evaluations confirm the potential of our method in achieving effective feature disentanglement.