Abstract

Estimating predictive uncertainty is crucial for many computer vision tasks, from image classification to autonomous driving systems. Hamiltonian Monte Carlo (HMC) is an sampling method for performing Bayesian inference. On the other hand, Dropout regularization has been proposed as an approximate model averaging technique that tends to improve generalization in large-scale models such as deep neural networks. Although HMC provides convergence guarantees for most standard Bayesian models, it do not handle discrete parameters arising from Dropout regularization. In this paper, we present a robust methodology for improving predictive uncertainty in classification problems, based on Dropout and HMC. Even though Dropout induces a non-smooth energy function with no such convergence guarantees, the resulting discretization of the Hamiltonian proves empirical success. The proposed method allows to effectively estimate the predictive accuracy and to provide better generalization for difficult test examples.