Variational Disentanglement for Domain Generalization

Domain generalization aims to learn a domain-invariant model that can generalize well to the unseen target domain. In this paper, based on the assumption that there exists an invariant feature mapping, we propose an evidence upper bound of the divergence between the category-specific feature and its invariant ground-truth using variational inference. To optimize this upper bound, we further propose an efficient Variational Disentanglement Network (VDN) that is capable of disentangling the domain-specific features and category-specific features (which generalize well to the unseen samples). Besides, the generated novel images from VDN are used to further improve the generalization ability. We conduct extensive experiments to verify our method on three benchmarks, and both quantitative and qualitative results illustrate the effectiveness of our method.