Laplace Approximation Based Epistemic Uncertainty Estimation in 3D Object Detection

Peng Yun, Ming Liu

Keywords: Laplace approximation, epistemic uncertainty, 3D object detection

TL;DR: In this work, we tailor Laplace approximation for 3D object detection, and propose solutions in Fisher approximation, Bayesian inference, and weight prior determination.

Abstract: Understanding the uncertainty of predictions is a desirable feature for perceptual modules in critical robotic applications. 3D object detectors are neural networks with high-dimensional output space. It suffers from poor calibration in classification and lacks reliable uncertainty estimation in regression. To provide a reliable epistemic uncertainty estimation, we tailor Laplace approximation for 3D object detectors, and propose an Uncertainty Separation and Aggregation pipeline for Bayesian inference. The proposed Laplace-approximation approach can easily convert a deterministic 3D object detector into a Bayesian neural network capable of estimating epistemic uncertainty. The experiment results on the KITTI dataset empirically validate the effectiveness of our proposed methods, and demonstrate that Laplace approximation performs better uncertainty quality than Monte-Carlo Dropout, DeepEnsembles, and deterministic models.

Student First Author: yes

Code: https://github.com/pyun-ram/OpenPCUCT