Sampling-Free Epistemic Uncertainty Estimation Using Approximated Variance Propagation
Authors:
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2931-2940
Abstract
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 (\ie, 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.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Uncertainty Estimation for Deep Neural Object Detectors in Safety-Critical Applications2018
- Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection2018
- Efficient Uncertainty Estimation for Semantic Segmentation in Videos2018
- Uncertainty-Aware Learning from Demonstration Using Mixture Density Networks with Sampling-Free Variance Modeling2018
- Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses2017
- Unsupervised Monocular Depth Estimation with Left-Right Consistency2017
- Semantic Segmentation of Small Objects and Modeling of Uncertainty in Urban Remote Sensing Images Using Deep Convolutional Neural Networks2016
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Semantic object classes in video: A high-definition ground truth databasePattern Recognition Letters, 2009
- On the Exact Variance of ProductsJournal of the American Statistical Association, 1960