提出新方法TAROT，让模型在不同环境下更抗干扰且泛化更强。
TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification
- 基于新发散度度量，推导出鲁棒风险的泛化界
- 在DomainNet上超越现有方法，提升准确率与鲁棒性
- 适合需要跨域稳定表现的实际应用
针对对抗攻击下的鲁棒域自适应问题，本文提出一种新的泛化界，基于专为鲁棒域适应设计的发散度度量。基于此，提出新算法TAROT，旨在同时提升域适应能力与鲁棒性。大量实验表明，TAROT不仅在准确率和鲁棒性上优于现有最先进方法，还显著增强域泛化与可扩展性，有效学习域不变特征。尤其在具有挑战性的DomainNet数据集上表现优异，验证了其在不同域（包括未见域）间学习强泛化表示的能力。这些结果凸显该方法在真实域自适应场景中的广泛适用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。