Object detection is a fundamental task in autonomous driving. Besides bounding-box-like detection algorithms, uncertainty estimation is necessary for safe and trust-worthy perceptions. Bayesian Neural Networks (BNNs) provide a reliable approach to address the challenge. However, it often becomes computationally prohibitive to apply them to modern large-scale neural networks. This work develops an efficient BNN by combining the Laplace Approximation (LA) with linearized inference. Specifically, we study the effectiveness and computational necessity of a diagonal Hessian approximation in the LA on over-parameterized networks. With numerous quantitative experiments on different types of interference, the proposed method demonstrates the ability for real-time and robust uncertainty description for autonomous driving.
Laplace Approximation for Real-Time Uncertainty Estimation in Object Detection
2022-10-08
2603304 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Laplace Approximation for Uncertainty Estimation of Deep Neural Networks
Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2019
|Uncertainty Estimation in One-Stage Object Detection
IEEE | 2019
|An approximation for inverse Laplace transforms
NTRS | 1981
|Method for Real-Time Frequency Response and Uncertainty Estimation
Online Contents | 2014
|