Mixstyle-Entropy: Domain Generalization with Causal Intervention and Perturbation
Mixstyle-Entropy：结合因果干预与扰动的域泛化
Despite the considerable advancements achieved by deep neural networks, their performance tends to degenerate when the test environment diverges from the training ones. Domain generalization (DG) solves this issue by learning representations independent of domain-related information, thus facilitating extrapolation to unseen environments. Existing approaches typically focus on formulating tailored training objectives to extract shared features from the source data. However,…