mlsanityData to 7 Oct 2026

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

arXiv 2211.06241 ↗First posted 11 Nov 2022cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 29 references that are in the map. First posted on arXiv 11 Nov 2022.

Builds on

23 of 29 references.

References · 23

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  7. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  8. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  9. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  10. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  11. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  12. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
11 more
  1. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  2. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  3. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  4. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  5. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  6. 20203D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentationcited by 58
  7. 2020Gradients as a Measure of Uncertainty in Neural Networkscited by 55
  8. 2020KPRNet: Improving projection-based LiDAR semantic segmentationcited by 47
  9. 2020Why is the Mahalanobis Distance Effective for Anomaly Detection?cited by 28
  10. 2020Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey and Experimental Studycited by 12
  11. 2020Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Cloudscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11
  2. 2026RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classescited by 0