Rethinking the Evaluation Protocol of Domain Generalization

Domain generalization aims to solve the challenge of Out-of-Distribution (OOD) generalization by leveraging common knowledge learned from multiple training domains to generalize to unseen test domains. To accurately evaluate the OOD generalization ability, it is necessary to ensure that test data information is unavailable. However, the current domain generalization protocol may still have potential test data information leakage. This paper examines the potential risks of test data information leakage in two aspects of the current protocol: pretraining on ImageNet and oracle model selection. We propose that training from scratch and using multiple test domains would result in a more precise evaluation of OOD generalization ability. We also rerun the algorithms with the modified protocol and introduce a new leaderboard to encourage future research in domain generalization with a fairer comparison.