SPDG-Net: Semantics Preserving Domain Augmentation through Style Interpolation for Multi-Source Domain Generalization

This paper focuses on domain generalization (DG), addressing the challenge of robust classifier learning from multiple source domains for generalizing to unseen ones. DG suffers from limited source domain diversity, which may hinder model generalization. Recent studies explore domain-augmentation strategies but struggle to maintain semantics while altering image styles and generate only a few pseudo domains. To tackle this, we introduce Semantics Preserving DG Network (SPDG-Net). SPDG-Net is a triplet-conditioned U-Net-based GAN that synthesizes various pseudo domains, preserving image semantics through a cycle-consistency constraint. Moreover, our style interpolation-based domain generation produces fine-grained synthetic domains, unlike existing models. We also propose recognizing image styles alongside object classes to reduce model bias. Our experiments across benchmark datasets consistently outperform recent literature in DG.