TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability

Documenti analoghi

• VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary
  di: Luo, Hanjun, et al.
  Pubblicazione: (2024)
• MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness
  di: Xu, Xiaoyun, et al.
  Pubblicazione: (2023)
• Language-Driven Anchors for Zero-Shot Adversarial Robustness
  di: Li, Xiao, et al.
  Pubblicazione: (2023)
• CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
  di: Zhang, Mingkun, et al.
  Pubblicazione: (2025)
• Zero-Shot Industrial Anomaly Segmentation with Image-Aware Prompt Generation
  di: Park, SoYoung, et al.
  Pubblicazione: (2025)