Uncertainty Estimation Using a Single Deep Deterministic Neural Network
Abstract
We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. Our approach, deterministic uncertainty quantification (DUQ), builds upon ideas of RBF networks. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models. By enforcing detectability of changes in the input using a gradient penalty, we are able to reliably detect out of distribution data. Our uncertainty quantification scales well to large datasets, and using a single model, we improve upon or match Deep Ensembles in out of distribution detection on notable difficult dataset pairs such as FashionMNIST vs. MNIST, and CIFAR-10 vs. SVHN.
Cite
@article{arxiv.2003.02037,
title = {Uncertainty Estimation Using a Single Deep Deterministic Neural Network},
author = {Joost van Amersfoort and Lewis Smith and Yee Whye Teh and Yarin Gal},
journal= {arXiv preprint arXiv:2003.02037},
year = {2020}
}