TY - GEN

T1 - Uncertainty Estimation and Out-of-Distribution Detection for LiDAR Scene Semantic Segmentation

AU - Shojaei Miandashti, Hanieh

AU - Zou, Qianqian

AU - Mehltretter, Max

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025/5/12

Y1 - 2025/5/12

N2 - Safe navigation in new environments requires autonomous vehicles and robots to accurately interpret their surroundings, relying on LiDAR scene segmentation, out-of-distribution (OOD) obstacle detection, and uncertainty computation. We propose a method to distinguish in-distribution (ID) from OOD samples and quantify both epistemic and aleatoric uncertainties using the feature space of a single deterministic model. After training a semantic segmentation network, a Gaussian Mixture Model (GMM) is fitted to its feature space. OOD samples are detected by checking if their squared Mahalanobis distances to each Gaussian component conform to a chi-squared distribution, eliminating the need for an additional OOD training set. Given that the estimated mean and covariance matrix of a multivariate Gaussian distribution follow Gaussian and Inverse-Wishart distributions, multiple GMMs are generated by sampling from these distributions to assess epistemic uncertainty through classification variability. Aleatoric uncertainty is derived from the entropy of responsibility values within Gaussian components. Comparing our method with deep ensembles and logit-sampling for uncertainty computation demonstrates its superior performance in real-world applications for quantifying epistemic and aleatoric uncertainty, as well as detecting OOD samples. While deep ensembles miss some highly uncertain samples, our method successfully detects them and assigns high epistemic uncertainty.

AB - Safe navigation in new environments requires autonomous vehicles and robots to accurately interpret their surroundings, relying on LiDAR scene segmentation, out-of-distribution (OOD) obstacle detection, and uncertainty computation. We propose a method to distinguish in-distribution (ID) from OOD samples and quantify both epistemic and aleatoric uncertainties using the feature space of a single deterministic model. After training a semantic segmentation network, a Gaussian Mixture Model (GMM) is fitted to its feature space. OOD samples are detected by checking if their squared Mahalanobis distances to each Gaussian component conform to a chi-squared distribution, eliminating the need for an additional OOD training set. Given that the estimated mean and covariance matrix of a multivariate Gaussian distribution follow Gaussian and Inverse-Wishart distributions, multiple GMMs are generated by sampling from these distributions to assess epistemic uncertainty through classification variability. Aleatoric uncertainty is derived from the entropy of responsibility values within Gaussian components. Comparing our method with deep ensembles and logit-sampling for uncertainty computation demonstrates its superior performance in real-world applications for quantifying epistemic and aleatoric uncertainty, as well as detecting OOD samples. While deep ensembles miss some highly uncertain samples, our method successfully detects them and assigns high epistemic uncertainty.

KW - Epistemic and aleatoric uncertainty quantification

KW - LiDAR scene semantic segmentation

KW - Out-of-distribution detection

UR - http://www.scopus.com/inward/record.url?scp=105007223597&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-91767-7_8

DO - 10.1007/978-3-031-91767-7_8

M3 - Conference contribution

AN - SCOPUS:105007223597

SN - 9783031917660

T3 - Lecture Notes in Computer Science

SP - 116

EP - 131

BT - Computer Vision – ECCV 2024 Workshops, Proceedings

A2 - Del Bue, Alessio

A2 - Canton, Cristian

A2 - Pont-Tuset, Jordi

A2 - Tommasi, Tatiana

PB - Springer Science and Business Media Deutschland GmbH

T2 - 18th European Conference on Computer Vision, ECCV 2024

Y2 - 29 September 2024 through 4 October 2024

ER -