Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
Machine Learning
2019-06-14 v1 Machine Learning
Abstract
In this work we aim to obtain computationally-efficient uncertainty estimates with deep networks. For this, we propose a modified knowledge distillation procedure that achieves state-of-the-art uncertainty estimates both for in and out-of-distribution samples. Our contributions include a) demonstrating and adapting to distillation's regularization effect b) proposing a novel target teacher distribution c) a simple augmentation procedure to improve out-of-distribution uncertainty estimates d) shedding light on the distillation procedure through comprehensive set of experiments.
Cite
@article{arxiv.1906.05419,
title = {Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation},
author = {Erik Englesson and Hossein Azizpour},
journal= {arXiv preprint arXiv:1906.05419},
year = {2019}
}
Comments
Submitted at the ICML 2019 Workshop on Uncertainty & Robustness in Deep Learning(poster & spotlight talk)