Zero Shot Domain Generalization
This addresses domain generalization for unseen domains with new classes, which is an incremental extension of existing DG methods.
The paper tackles the problem of domain generalization where the unseen domain may also have new classes, introducing Zero-Shot Domain Generalization as a novel setting. It proposes a strategy using semantic class information to adapt existing methods, achieving strong baselines on datasets like CIFAR-10, CIFAR-100, F-MNIST, and PACS.
Standard supervised learning setting assumes that training data and test data come from the same distribution (domain). Domain generalization (DG) methods try to learn a model that when trained on data from multiple domains, would generalize to a new unseen domain. We extend DG to an even more challenging setting, where the label space of the unseen domain could also change. We introduce this problem as Zero-Shot Domain Generalization (to the best of our knowledge, the first such effort), where the model generalizes across new domains and also across new classes in those domains. We propose a simple strategy which effectively exploits semantic information of classes, to adapt existing DG methods to meet the demands of Zero-Shot Domain Generalization. We evaluate the proposed methods on CIFAR-10, CIFAR-100, F-MNIST and PACS datasets, establishing a strong baseline to foster interest in this new research direction.