Uncertainty Calibration Error: A New Metric for Multi-Class Classification

Various metrics have recently been proposed to measure uncertainty calibration of deep models for classification. However, these metrics either fail to capture miscalibration correctly or lack interpretability. We propose to use the normalized entropy as a measure of uncertainty and derive the Uncertainty Calibration Error (UCE), a comprehensible calibration metric for multi-class classification. In our experiments, we focus on uncertainty from variational Bayesian inference methods and compare UCE to established calibration errors on the task of multi-class image classification. UCE avoids several pathologies of other metrics, but does not sacrifice interpretability. It can be used for regularization to improve calibration during training without penalizing predictions with justified high confidence.