通过几何引导的对抗扰动，实现更精准的域间流形对齐。
GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation
- 利用流形切空间探索与约束优化，生成结构化对抗扰动。
- 在DomainNet等数据集上，少样本设置下准确率提升3.2%以上。
- 适合需要强鲁棒性与跨域一致性的迁移学习场景。
当源域与目标域之间存在显著流形差异时，领域自适应仍具挑战性。尽管现有方法利用流形感知的对抗扰动进行数据增强，但常忽略精确的流形对齐和结构化扰动的系统探索。为此，我们提出GAMA（Geometry-Aware Manifold Alignment），一种通过几何信息引导的对抗扰动实现显式流形对齐的结构化框架。GAMA系统地采用切空间探索与流形约束的对抗优化，在提升语义一致性、抵御离流形偏差的同时增强跨域对齐能力。理论分析表明，GAMA通过结构化正则化与显式对齐收紧了泛化界。在DomainNet、VisDA和Office-Home上的实验结果表明，GAMA在无监督及少样本设置下均持续优于现有对抗与自适应方法，展现出更优的鲁棒性、泛化能力与流形对齐性能。
原文摘要 · Abstract (English)
Domain adaptation remains a challenge when there is significant manifold discrepancy between source and target domains. Although recent methods leverage manifold-aware adversarial perturbations to perform data augmentation, they often neglect precise manifold alignment and systematic exploration of structured perturbations. To address this, we propose GAMA (Geometry-Aware Manifold Alignment), a structured framework that achieves explicit manifold alignment via adversarial perturbation guided by geometric information. GAMA systematically employs tangent space exploration and manifold-constrained adversarial optimization, simultaneously enhancing semantic consistency, robustness to off-manifold deviations, and cross-domain alignment. Theoretical analysis shows that GAMA tightens the generalization bound via structured regularization and explicit alignment. Empirical results on DomainNet, VisDA, and Office-Home demonstrate that GAMA consistently outperforms existing adversarial and adaptation methods in both unsupervised and few-shot settings, exhibiting superior robustness, generalization, and manifold alignment capability.
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。