Geometrically Regularized Transfer Learning with On-Manifold and Off-Manifold Perturbation

Documenti analoghi

• Disentangled Geometric Alignment with Adaptive Contrastive Perturbation for Reliable Domain Transfer
  di: Collins, Emma, et al.
  Pubblicazione: (2025)
• On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning
  di: Satou, Hana, et al.
  Pubblicazione: (2025)
• Fusing Physics-Driven Strategies and Cross-Modal Adversarial Learning: Toward Multi-Domain Applications
  di: Satou, Hana, et al.
  Pubblicazione: (2024)
• GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation
  di: Satou, Hana, et al.
  Pubblicazione: (2025)
• Dynamic Epsilon Scheduling: A Multi-Factor Adaptive Perturbation Budget for Adversarial Training
  di: Mitkiy, Alan, et al.
  Pubblicazione: (2025)