Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder

Documenti analoghi

• There is More to Attention: Statistical Filtering Enhances Explanations in Vision Transformers
  di: Ayyar, Meghna P, et al.
  Pubblicazione: (2025)
• Identifying Surgical Instruments in Laparoscopy Using Deep Learning Instance Segmentation
  di: Kletz, Sabrina, et al.
  Pubblicazione: (2025)
• Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation
  di: Sirotkin, Kirill, et al.
  Pubblicazione: (2024)
• Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging
  di: Yang, Yuzhe, et al.
  Pubblicazione: (2024)
• Object segmentation in the wild with foundation models: application to vision assisted neuro-prostheses for upper limbs
  di: Atoki, Bolutife, et al.
  Pubblicazione: (2025)