2 papers
cs.LG2025
Uncertainty-Aware Post-Hoc Calibration: Mitigating Confidently Incorrect Predictions Beyond Calibration Metrics
Hassan Gharoun, Mohammad Sadegh Khorshidi, Kasra Ranjbarigderi +2
Despite extensive research on neural network calibration, existing methods typically apply global transformations that treat all predictions uniformly, overlooking the heterogeneou…
cs.CV2025
Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks
Hassan Gharoun, Mohammad Sadegh Khorshidi, Kasra Ranjbarigderi +2
This work proposes an evidence-retrieval mechanism for uncertainty-aware decision-making that replaces a single global cutoff with an evidence-conditioned, instance-adaptive criter…