On the calibration of underrepresented classes in LiDAR-based semantic segmentation
Not on the map. Why?
Abstract (arXiv)
The calibration of deep learning-based perception models plays a crucial role in their reliability. Our work focuses on a class-wise evaluation of several model's confidence performance for LiDAR-based semantic segmentation with the aim of providing insights into the calibration of underrepresented classes. Those classes often include VRUs and are thus of particular interest for safety reasons. With the help of a metric based on sparsification curves we compare the calibration abilities of three semantic segmentation models with different architectural concepts, each in a in deterministic and a probabilistic version. By identifying and describing the dependency between the predictive performance of a class and the respective calibration quality we aim to facilitate the model selection and refinement for safety-critical applications.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 13 Oct 2022.
Builds on
27 of 34 references.
References · 27
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
- 2018PointCNN: Convolution On X-Transformed Pointscited by 764
- 2019Measuring Calibration in Deep Learningcited by 446
- 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
- 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
- 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
- 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
- 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
15 more
- 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
- 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
- 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
- 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
- 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
- 2020Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systemscited by 100
- 2018VV-Net: Voxel VAE Net with Group Convolutions for Point Cloud Segmentationcited by 64
- 2021Understanding Softmax Confidence and Uncertaintycited by 63
- 2019SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Drivingcited by 57
- 2020Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Studycited by 33
- 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
- 2017ProbFlow: Joint Optical Flow and Uncertainty Estimationcited by 24
- 2020A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applicationscited by 19
- 2018Boosting LiDAR-based Semantic Labeling by Cross-Modal Training Data Generationcited by 14
- 2021Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shiftcited by 8
Built on by
Citing papers per year: 2024: 1.
1 paper.
- 2024Decoupling of neural network calibration measurescited by 3
- 2024Decoupling of neural network calibration measures4 Jun 2024