# Domain Generalization by Solving Jigsaw Puzzles

## TL;DR

This paper introduces a novel domain generalization method that combines supervised object recognition with self-supervised jigsaw puzzle solving, improving performance across multiple datasets.

## Contribution

The paper proposes a combined supervised and self-supervised learning approach using jigsaw puzzles to enhance domain generalization in object recognition.

## Key findings

- Outperforms previous domain generalization methods on multiple datasets
- Self-supervised jigsaw task improves spatial concept learning
- Regularization effect enhances model robustness

## Abstract

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.