Uncertainty Estimation Using a Single Deep Deterministic Neural Network
Joost Van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal
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.
BibTeX
@InProceedings{pmlr-v119-van-amersfoort20a,
title = {Uncertainty Estimation Using a Single Deep Deterministic Neural Network},
author = {Van Amersfoort, Joost and Smith, Lewis and Teh, Yee Whye and Gal, Yarin},
booktitle = {Proceedings of the 37th International Conference on Machine Learning},
pages = {9690--9700},
year = {2020},
editor = {III, Hal Daumé and Singh, Aarti},
volume = {119},
series = {Proceedings of Machine Learning Research},
month = {13--18 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v119/van-amersfoort20a/van-amersfoort20a.pdf},
url = {https://proceedings.mlr.press/v119/van-amersfoort20a.html},
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.}
}