Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy

Documenti analoghi

• Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
  di: Wang, Yanyun, et al.
  Pubblicazione: (2026)
• Saliency-Guided Training for Fingerprint Presentation Attack Detection
  di: Webster, Samuel, et al.
  Pubblicazione: (2025)
• Divisive Decisions: Improving Salience-Based Training for Generalization in Binary Classification Tasks
  di: Piland, Jacob, et al.
  Pubblicazione: (2025)
• Almost Right: Making First-Layer Kernels Nearly Orthogonal Improves Model Generalization
  di: Crum, Colton R., et al.
  Pubblicazione: (2025)
• Grains of Saliency: Optimizing Saliency-based Training of Biometric Attack Detection Models
  di: Crum, Colton R., et al.
  Pubblicazione: (2024)