TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification
This addresses the problem of maintaining model performance across diverse and adversarial domains for real-world domain adaptation applications.
The paper tackles robust domain adaptation against adversarial attacks by proposing TAROT, a new algorithm that achieves state-of-the-art accuracy and robustness on the DomainNet dataset while enhancing domain generalization and scalability.
Robust domain adaptation against adversarial attacks is a critical research area that aims to develop models capable of maintaining consistent performance across diverse and challenging domains. In this paper, we derive a new generalization bound for robust risk on the target domain using a novel divergence measure specifically designed for robust domain adaptation. Building upon this, we propose a new algorithm named TAROT, which is designed to enhance both domain adaptability and robustness. Through extensive experiments, TAROT not only surpasses state-of-the-art methods in accuracy and robustness but also significantly enhances domain generalization and scalability by effectively learning domain-invariant features. In particular, TAROT achieves superior performance on the challenging DomainNet dataset, demonstrating its ability to learn domain-invariant representations that generalize well across different domains, including unseen ones. These results highlight the broader applicability of our approach in real-world domain adaptation scenarios.