RADMI: Latent Information Aggregation as a Proxy for Model Uncertainty

Documenti analoghi

• VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability
  di: Prabhushankar, Mohit, et al.
  Pubblicazione: (2024)
• Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks
  di: Prabhushankar, Mohit, et al.
  Pubblicazione: (2024)
• Perceptual Quality-based Model Training under Annotator Label Uncertainty
  di: Zhou, Chen, et al.
  Pubblicazione: (2024)
• Information Router for Mitigating Modality Dominance in Vision-Language Models
  di: Kim, Seulgi, et al.
  Pubblicazione: (2026)
• BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation
  di: Chowdhury, Prithwijit, et al.
  Pubblicazione: (2026)