Domain Generalization by Solving Jigsaw Puzzles
This addresses the problem of domain generalization for object recognition, offering a simple method that is incremental but effective in enhancing model robustness across varied data sources.
The paper tackles object recognition across domains by combining supervised learning with a self-supervised jigsaw puzzle task to improve generalization, achieving performance that outperforms previous domain generalization and adaptation solutions on datasets like PACS, VLCS, Office-Home, and digits.
Human adaptability relies crucially on the ability to learn and merge knowledge both from supervised and unsupervised learning: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly effective, because supervised learning can never be exhaustive and thus learning autonomously allows to discover invariances and regularities that help to generalize. In this paper we propose to apply a similar approach to the task of object recognition across domains: our model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals how to solve a jigsaw puzzle on the same images. This secondary task helps the network to learn the concepts of spatial correlation while acting as a regularizer for the classification task. Multiple experiments on the PACS, VLCS, Office-Home and digits datasets confirm our intuition and show that this simple method outperforms previous domain generalization and adaptation solutions. An ablation study further illustrates the inner workings of our approach.