Reducing Bias in Pre-trained Models by Tuning while Penalizing Change

Documenti analoghi

• When Medical Imaging Met Self-Attention: A Love Story That Didn't Quite Work Out
  di: Piater, Tristan, et al.
  Pubblicazione: (2024)
• Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients
  di: Penzel, Niklas, et al.
  Pubblicazione: (2025)
• Facing Asymmetry -- Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventions
  di: Büchner, Tim, et al.
  Pubblicazione: (2024)
• The Power of Properties: Uncovering the Influential Factors in Emotion Classification
  di: Büchner, Tim, et al.
  Pubblicazione: (2024)
• FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
  di: Schmalwasser, Laines, et al.
  Pubblicazione: (2025)