-
Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning
Post-hoc calibration is a common approach for providing high-quality con...
06/23/2020 ∙ by Kanil Patel, et al. ∙
0
∙
share
read it
-
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
Uncertainty estimates help to identify ambiguous, novel, or anomalous in...
12/16/2019 ∙ by Kanil Patel, et al. ∙
22
∙
share
read it
