On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning

Documenti analoghi

• Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection
  di: Li, Yushu, et al.
  Pubblicazione: (2024)
• Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization
  di: Su, Yongyi, et al.
  Pubblicazione: (2023)
• Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model
  di: Li, Yushu, et al.
  Pubblicazione: (2024)
• Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training
  di: Lin, Jinpeng, et al.
  Pubblicazione: (2024)
• Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
  di: Zhang, Haojie, et al.
  Pubblicazione: (2023)