BendVLM: Test-Time Debiasing of Vision-Language Embeddings

Documenti analoghi

• Identifying Implicit Social Biases in Vision-Language Models
  di: Hamidieh, Kimia, et al.
  Pubblicazione: (2024)
• Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
  di: Hamidieh, Kimia, et al.
  Pubblicazione: (2024)
• MaskMedPaint: Masked Medical Image Inpainting with Diffusion Models for Mitigation of Spurious Correlations
  di: Jin, Qixuan, et al.
  Pubblicazione: (2024)
• SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models
  di: Ranjbar, Sepehr Kazemi, et al.
  Pubblicazione: (2025)
• Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
  di: Hamidieh, Kimia, et al.
  Pubblicazione: (2026)