Guardado en:
Detalles Bibliográficos
Autores principales: Satou, Hana, Monkey, F
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.15194
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910959188049920
author Satou, Hana
Monkey, F
author_facet Satou, Hana
Monkey, F
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15194
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation
Satou, Hana
Monkey, F
Computer Vision and Pattern Recognition
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.
title GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.15194