Volltext-Downloads (blau) und Frontdoor-Views (grau)

A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation

  • Safety-critical applications like autonomous driving use Deep Neural Networks (DNNs) for object detection and segmentation. The DNNs fail to predict when they observe an Out-of-Distribution (OOD) input leading to catastrophic consequences. Existing OOD detection methods were extensively studied for image inputs but have not been explored much for LiDAR inputs. So in this study, we proposed two datasets for benchmarking OOD detection in 3D semantic segmentation. We used Maximum Softmax Probability and Entropy scores generated using Deep Ensembles and Flipout versions of RandLA-Net as OOD scores. We observed that Deep Ensembles out perform Flipout model in OOD detection with greater AUROC scores for both datasets.

Export metadata

Additional Services

Search Google Scholar Check availability


Show usage statistics
Document Type:Preprint
Author:Lokesh Veeramacheneni, Matias Valdenegro-Toro
Number of pages:4
ArXiv Id:http://arxiv.org/abs/2211.06241v1
Date of first publication:2022/11/11
Robot Learning Workshop @ NeurIPS 2022
Departments, institutes and facilities:Fachbereich Informatik
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Entry in this database:2022/12/08