Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference

09/30/2019

∙

by   Max-Heinrich Laves, et al.

∙

0

∙

share

In this paper, well-calibrated model uncertainty is obtained by using temperature scaling together with Monte Carlo dropout as approximation to Bayesian inference. The proposed approach can easily be derived from frequentist temperature scaling and yields well-calibrated model uncertainty as well as softmax likelihood.