Towards Shape Biased Unsupervised Representation Learning for Domain Generalization
This work addresses domain generalization for computer vision by enhancing shape bias, which is incremental as it builds on existing self-supervised methods.
The paper tackles the problem of improving shape bias in self-supervised learning for domain generalization, proposing a framework that integrates domain diversification and jigsaw puzzles to achieve state-of-the-art performance on multiple datasets.
It is known that, without awareness of the process, our brain appears to focus on the general shape of objects rather than superficial statistics of context. On the other hand, learning autonomously allows discovering invariant regularities which help generalization. In this work, we propose a learning framework to improve the shape bias property of self-supervised methods. Our method learns semantic and shape biased representations by integrating domain diversification and jigsaw puzzles. The first module enables the model to create a dynamic environment across arbitrary domains and provides a domain exploration vs. exploitation trade-off, while the second module allows the model to explore this environment autonomously. This universal framework does not require prior knowledge of the domain of interest. Extensive experiments are conducted on several domain generalization datasets, namely, PACS, Office-Home, VLCS, and Digits. We show that our framework outperforms state-of-the-art domain generalization methods by a large margin.