Details
Originalsprache | Englisch |
---|---|
Titel des Sammelwerks | Computer Vision – ECCV 2024 Workshops, Proceedings |
Herausgeber/-innen | Alessio Del Bue, Cristian Canton, Jordi Pont-Tuset, Tatiana Tommasi |
Herausgeber (Verlag) | Springer Science and Business Media Deutschland GmbH |
Seiten | 116-131 |
Seitenumfang | 16 |
ISBN (elektronisch) | 978-3-031-91767-7 |
ISBN (Print) | 9783031917660 |
Publikationsstatus | Veröffentlicht - 12 Mai 2025 |
Veranstaltung | 18th European Conference on Computer Vision, ECCV 2024 - Milan, Italien Dauer: 29 Sept. 2024 → 4 Okt. 2024 |
Publikationsreihe
Name | Lecture Notes in Computer Science |
---|---|
Band | 15629 LNCS |
ISSN (Print) | 0302-9743 |
ISSN (elektronisch) | 1611-3349 |
Abstract
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.
ASJC Scopus Sachgebiete
- Mathematik (insg.)
- Theoretische Informatik
- Informatik (insg.)
- Allgemeine Computerwissenschaft
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Computer Vision – ECCV 2024 Workshops, Proceedings. Hrsg. / Alessio Del Bue; Cristian Canton; Jordi Pont-Tuset; Tatiana Tommasi. Springer Science and Business Media Deutschland GmbH, 2025. S. 116-131 (Lecture Notes in Computer Science; Band 15629 LNCS).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
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 -