mlsanityData to 14 Oct 2026

False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation

arXiv 2110.15681 ↗First posted 29 Oct 2021cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

We present a novel post-processing tool for semantic segmentation of LiDAR point cloud data, called LidarMetaSeg, which estimates the prediction quality segmentwise. For this purpose we compute dispersion measures based on network probability outputs as well as feature measures based on point cloud input features and aggregate them on segment level. These aggregated measures are used to train a meta classification model to predict whether a predicted segment is a false positive or not and a meta regression model to predict the segmentwise intersection over union. Both models can then be applied to semantic segmentation inferences without knowing the ground truth. In our experiments we use different LiDAR segmentation models and datasets and analyze the power of our method. We show that our results outperform other standard approaches.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 29 Oct 2021.

Builds on

22 of 28 references.

References · 22

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  8. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  9. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  10. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  11. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  12. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
10 more
  1. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  2. 2018Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detectioncited by 82
  3. 2018Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilitiescited by 54
  4. 2020Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Studycited by 33
  5. 2020MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Mapscited by 23
  6. 2018Inherent Brain Segmentation Quality Control from Fully ConvNet Monte Carlo Samplingcited by 20
  7. 2019Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networkscited by 20
  8. 2019Uncertainty Measures and Prediction Quality Rating for the Semantic Segmentation of Nested Multi Resolution Street Scene Imagescited by 18
  9. 2017Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detectioncited by 11
  10. 2019MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentationcited by 8

Built on by

Cited by year

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

2 papers.

  1. 2022Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantificationcited by 20
  2. 2024Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networkscited by 0