MetaDefa: Meta-learning based on Domain Enhancement and Feature Alignment for Single Domain Generalization
This work addresses domain-shift issues in computer vision, offering an incremental improvement for applications requiring robust generalization from a single source domain.
The paper tackles the problem of single domain generalization (SDG) by proposing MetaDefa, a meta-learning method that uses domain enhancement and feature alignment to improve model generalization, achieving significant performance advantages in unknown target domains on two public datasets.
The single domain generalization(SDG) based on meta-learning has emerged as an effective technique for solving the domain-shift problem. However, the inadequate match of data distribution between source and augmented domains and difficult separation of domain-invariant features from domain-related features make SDG model hard to achieve great generalization. Therefore, a novel meta-learning method based on domain enhancement and feature alignment (MetaDefa) is proposed to improve the model generalization performance. First, the background substitution and visual corruptions techniques are used to generate diverse and effective augmented domains. Then, the multi-channel feature alignment module based on class activation maps and class agnostic activation maps is designed to effectively extract adequate transferability knowledge. In this module, domain-invariant features can be fully explored by focusing on similar target regions between source and augmented domains feature space and suppressing the feature representation of non-similar target regions. Extensive experiments on two publicly available datasets show that MetaDefa has significant generalization performance advantages in unknown multiple target domains.