TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models

Documenti analoghi

• RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
  di: Varma, Maya, et al.
  Pubblicazione: (2024)
• LieRE: Lie Rotational Positional Encodings
  di: Ostmeier, Sophie, et al.
  Pubblicazione: (2024)
• Learning Generalizable 3D Medical Image Representations from Mask-Guided Self-Supervision
  di: Gao, Yunhe, et al.
  Pubblicazione: (2026)
• From Detection to Mitigation: Addressing Bias in Deep Learning Models for Chest X-Ray Diagnosis
  di: Mottez, Clemence, et al.
  Pubblicazione: (2025)
• Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models
  di: Zhang, Yabin, et al.
  Pubblicazione: (2026)