SINGLE-DOMAIN GENERALIZATION FOR SEMANTIC SEGMENTATION VIA DUAL-LEVEL DOMAIN AUGMENTATION

The goal of single-domain generalization is to learn a domain-generalized model from only one single source domain. To avoid overfitting to the source domain, recent research focused on domain augmentation for learning domain generalized features. Therefore, domain diversity is indeed crucial to the generalization ability of the model. In this paper, we propose a novel dual-level domain augmentation framework to enrich the domain diversity for single-domain generalized semantic segmentation. We specifically devise an Image-Level and a Class-Level Augmentation Modules (IAM and CAM) to enlarge the diversity of augmented images and per-class features, respectively. From the original and augmented data, we then design a Domain-Generalized Feature Learning to learn representative features regularized by a large-scale pre-trained model. Experimental results on semantic segmentation benchmarks demonstrate the effectiveness and outperformance of the proposed method over previous work.