用对抗扰动增强模型跨域适应能力，提升鲁棒性与泛化性能。
On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning
- 将对抗样本作为数据增强手段，优化决策边界并减少对源域特征的过拟合。
- 在VisDA、DomainNet等数据集上，少样本和无监督迁移场景下性能显著提升。
- 适合关注模型鲁棒性与跨域适应性的研究者和工程应用者。
跨域分布偏移下的迁移学习仍是构建鲁棒自适应机器学习系统的核心挑战。尽管对抗扰动传统上被视为暴露模型弱点的威胁，但近期研究表明其也可作为数据增强的建设性工具。本文系统研究了对抗数据增强（ADA）在提升迁移学习中鲁棒性与适应性方面的作用。通过在训练中策略性地引入对抗样本，改善决策边界并降低对源域特定特征的过拟合，从而增强域泛化能力。进一步提出统一框架，融合ADA、一致性正则化与域不变表示学习。在VisDA、DomainNet和Office-Home等多个基准数据集上的大量实验表明，该方法在无监督及少样本域适应设置下均持续提升目标域性能。结果揭示了对抗学习的建设性视角，将扰动从破坏性攻击转化为促进跨域可迁移性的正则化力量。
原文摘要 · Abstract (English)
Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model vulnerabilities, recent studies suggest that they can also serve as constructive tools for data augmentation. In this work, we systematically investigate the role of adversarial data augmentation (ADA) in enhancing both robustness and adaptivity in transfer learning settings. We analyze how adversarial examples, when used strategically during training, improve domain generalization by enriching decision boundaries and reducing overfitting to source-domain-specific features. We further propose a unified framework that integrates ADA with consistency regularization and domain-invariant representation learning. Extensive experiments across multiple benchmark datasets -- including VisDA, DomainNet, and Office-Home -- demonstrate that our method consistently improves target-domain performance under both unsupervised and few-shot domain adaptation settings. Our results highlight a constructive perspective of adversarial learning, transforming perturbation from a destructive attack into a regularizing force for cross-domain transferability.
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。