Approaching Neural Network Uncertainty Realism
arXiv:2101.02974
Abstract
Statistical models are inherently uncertain. Quantifying or at least upper-bounding their uncertainties is vital for safety-critical systems such as autonomous vehicles. While standard neural networks do not report this information, several approaches exist to integrate uncertainty estimates into them. Assessing the quality of these uncertainty estimates is not straightforward, as no direct ground truth labels are available. Instead, implicit statistical assessments are required. For regression, we propose to evaluate uncertainty realism -- a strict quality criterion -- with a Mahalanobis distance-based statistical test. An empirical evaluation reveals the need for uncertainty measures that are appropriate to upper-bound heavy-tailed empirical errors. Alongside, we transfer the variational U-Net classification architecture to standard supervised image-to-image tasks. We adopt it to the automotive domain and show that it significantly improves uncertainty realism compared to a plain encoder-decoder model.
Accepted at the NeurIPS 2019 Workshop on Machine Learning for Autonomous Driving (ML4AD)
References in corpus (9)
- End to End Learning for Self-Driving Cars
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Weight Uncertainty in Neural Networks
- Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
- Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
- Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
- Bayesian deep neural networks for low-cost neurophysiological markers of Alzheimer's disease severity
- Known Unknowns: Uncertainty Quality in Bayesian Neural Networks