Calibration of Model Uncertainty for Dropout Variational Inference
This work addresses uncertainty calibration for reliable prediction rejection and out-of-distribution detection in deep learning, but it is incremental as it builds on existing logit scaling techniques.
The paper tackled the miscalibration of model uncertainty in dropout variational inference by extending logit scaling methods, reducing miscalibration as measured by Expected Uncertainty Calibration Error (UCE) on datasets like CIFAR-10/100 and SVHN.
The model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. In this paper, different logit scaling methods are extended to dropout variational inference to recalibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration. The effectiveness of recalibration is evaluated on CIFAR-10/100 and SVHN for recent CNN architectures. Experimental results show that logit scaling considerably reduce miscalibration by means of UCE. Well-calibrated uncertainty enables reliable rejection of uncertain predictions and robust detection of out-of-distribution data.