Restoration towards decomposition: A simple approach for domain generalization

• Published in: Information sciences 2024-09, Vol.679, p.121053, Article 121053
• Main Authors: Li, Mengwei, Wang, Zilei, Hu, Xiaoming
• Format: Article
• Language: English
• Subjects: Adversarial training; Contrastive learning; Domain generalization; Meta-learning
• ISSN: 0020-0255; 1872-6291
• DOI: 10.1016/j.ins.2024.121053

Domain generalization (DG) aims to train a model capable of generalizing to unseen target domains by utilizing data from multiple disjoint source domains. Previous domain generalization methods primarily utilize data augmentation and domain-invariant feature learning. However, since the target domain is unknown, data augmentation methods struggle to generate images or features that closely resemble the target domain. In addition, existing domain-invariant feature learning methods are incapable of achieving complete decoupling, resulting in misalignment of feature distribution between the source and target domains. Hence, in this work, we propose a new perspective to address domain generalization by focusing on learning the ability to transform the target domain visual representations into those of the source domain. If the style of the unknown target domain can be transformed into the style of the known source domain, the adverse effects of domain shift can be effectively mitigated. Following this line of thought, we have developed a meta-learning task named “feature restoration” aimed at training a model to acquire this capability. Specifically, feature restoration involves replacing the domain-specific components within the visual representations of the target domain with those of the source domain. Experimental results on five DG benchmarks reveal that our method can achieve state-of-the-art performance. Ablation studies and visualization results further demonstrate the rationality and effectiveness of our design.