mlsanityData to 7 Oct 2026

Low-Resource White-Box Semantic Segmentation of Supporting Towers on 3D Point Clouds via Signature Shape Identification

arXiv 2306.07809 ↗First posted 13 Jun 2023cs.CV cs.LG math.GTcited by 2

Not on the map. Why?

Abstract (arXiv)

Research in 3D semantic segmentation has been increasing performance metrics, like the IoU, by scaling model complexity and computational resources, leaving behind researchers and practitioners that (1) cannot access the necessary resources and (2) do need transparency on the model decision mechanisms. In this paper, we propose SCENE-Net, a low-resource white-box model for 3D point cloud semantic segmentation. SCENE-Net identifies signature shapes on the point cloud via group equivariant non-expansive operators (GENEOs), providing intrinsic geometric interpretability. Our training time on a laptop is 85~min, and our inference time is 20~ms. SCENE-Net has 11 trainable geometrical parameters and requires fewer data than black-box models. SCENE--Net offers robustness to noisy labeling and data imbalance and has comparable IoU to state-of-the-art methods. With this paper, we release a 40~000 Km labeled dataset of rural terrain point clouds and our code implementation.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 50 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

35 of 50 references.

References · 35

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  7. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  8. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 844
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  11. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  12. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
23 more
  1. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  2. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  3. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  4. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  5. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  6. 2017Tversky loss function for image segmentation using 3D fully convolutional deep networkscited by 228
  7. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  8. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  9. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  10. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  11. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  12. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  13. 2017Interpretable Convolutional Neural Networkscited by 161
  14. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  15. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  16. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  17. 2017Pointwise Convolutional Neural Networkscited by 126
  18. 2020Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challengescited by 80
  19. 2018Fully-Convolutional Point Networks for Large-Scale Point Cloudscited by 44
  20. 2019Geometry Sharing Network for 3D Point Cloud Classification and Segmentationcited by 33
  21. 2018Towards a topological-geometrical theory of group equivariant non-expansive operators for data analysis and machine learningcited by 24
  22. 2022GENEOnet: A new machine learning paradigm based on Group Equivariant Non-Expansive Operators. An application to protein pocket detectioncited by 4
  23. 2021On the geometric and Riemannian structure of the spaces of group equivariant non-expansive operatorscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025GENEOnet: Statistical analysis supporting explainability and trustworthinesscited by 0
  2. 2026GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layercited by 0