Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation

08/01/2019
by   Janis Postels, et al.
1

We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents how much one can trust predictions on new data. Recently promising works were proposed using noise injection combined with Monte-Carlo sampling at inference time to estimate this quantity (e.g. Monte-Carlo dropout). Our main contribution is an approximation of the epistemic uncertainty estimated by these methods that does not require sampling, thus notably reducing the computational overhead. We apply our approach to large-scale visual tasks (i.e., semantic segmentation and depth regression) to demonstrate the advantages of our method compared to sampling-based approaches in terms of quality of the uncertainty estimates as well as of computational overhead.

READ FULL TEXT

page 1

page 5

page 7

page 8

research
08/25/2023

Escaping the Sample Trap: Fast and Accurate Epistemic Uncertainty Estimation with Pairwise-Distance Estimators

This work introduces a novel approach for epistemic uncertainty estimati...
research
08/20/2019

n-MeRCI: A new Metric to Evaluate the Correlation Between Predictive Uncertainty and True Error

As deep learning applications are becoming more and more pervasive in ro...
research
10/06/2020

Real-time Uncertainty Decomposition for Online Learning Control

Safety-critical decisions based on machine learning models require a cle...
research
09/05/2022

Improving Out-of-Distribution Detection via Epistemic Uncertainty Adversarial Training

The quantification of uncertainty is important for the adoption of machi...
research
08/04/2020

On Feature Relevance Uncertainty: A Monte Carlo Dropout Sampling Approach

Understanding decisions made by neural networks is key for the deploymen...
research
09/20/2019

Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Bias

Supporting model interpretability for complex phenomena where annotators...
research
10/27/2020

Know Where To Drop Your Weights: Towards Faster Uncertainty Estimation

Estimating epistemic uncertainty of models used in low-latency applicati...

Please sign up or login with your details

Forgot password? Click here to reset