Domain Generalization vs Data Augmentation: An Unbiased Perspective

Francesco Cappio Borlino, Antonio D'Innocente, Tatiana Tommasi

Abstract: In domain generalization the target domain is not known at training time. We show that a style transfer based data augmentation strategy can be implemented easily and outperforms the current state of the art domain generalization methods. Moreover, we observe that those methods, even if combined with the described data augmentation, do not take advantage of it, indicating the need of new generalization solutions.