We benchmark the robustness of maximum likelihood based uncertainty estimation methods to outliers in training data for regression tasks. Outliers or noisy labels in training data results in degraded performances as well as incorrect estimation of uncertainty. We propose the use of a heavy-tailed distribution (Laplace distribution) to improve the robustness to outliers. This property is evaluated using standard regression benchmarks and on a high-dimensional regression task of monocular depth estimation, both containing outliers. In particular, heavy-tailed distribution based maximum likelihood provides better uncertainty estimates, better separation in uncertainty for out-of-distribution data, as well as better detection of adversarial attacks in the presence of outliers.
Maximum Likelihood Uncertainty Estimation: Robustness to Outliers
2022-03-01
Conference paper
Electronic Resource
English
Uncertainty identification by the maximum likelihood method
Online Contents | 2005
|Maximum-Likelihood Parameter-Estimation Algorithm
NTRS | 1986
|MAXIMUM-LIKELIHOOD GPS PARAMETER ESTIMATION
British Library Online Contents | 2005
|MAXIMUM-LIKELIHOOD GPS PARAMETER ESTIMATION
Online Contents | 2005
|