On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning
This work addresses the problem of building robust and adaptable machine learning systems for researchers and practitioners in transfer learning, offering an incremental advancement by integrating ADA with existing techniques.
The paper tackles the challenge of transfer learning across domains with distribution shift by investigating adversarial data augmentation (ADA) as a tool to enhance robustness and adaptivity, demonstrating consistent improvements in target-domain performance across multiple benchmark datasets.
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.