mlsanityData to 14 Oct 2026

Visualizing Global Explanations of Point Cloud DNNs

arXiv 2203.09505 ↗First posted 17 Mar 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

In the field of autonomous driving and robotics, point clouds are showing their excellent real-time performance as raw data from most of the mainstream 3D sensors. Therefore, point cloud neural networks have become a popular research direction in recent years. So far, however, there has been little discussion about the explainability of deep neural networks for point clouds. In this paper, we propose a point cloud-applicable explainability approach based on a local surrogate model-based method to show which components contribute to the classification. Moreover, we propose quantitative fidelity validations for generated explanations that enhance the persuasive power of explainability and compare the plausibility of different existing point cloud-applicable explainability methods. Our new explainability approach provides a fairly accurate, more semantically coherent and widely applicable explanation for point cloud classification tasks. Our code is available at https://github.com/Explain3D/LIME-3D

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

30 of 45 references.

References · 30

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2016Improved Techniques for Training GANscited by 2,970
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  10. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  11. 2018Sanity Checks for Saliency Mapscited by 1,156
  12. 2017SmoothGrad: removing noise by adding noisecited by 1,109
18 more
  1. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  2. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  3. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  4. 2016Synthesizing the preferred inputs for neurons in neural networks via deep generator networkscited by 181
  5. 2018PointCloud Saliency Mapscited by 112
  6. 2016Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networkscited by 106
  7. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  8. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  9. 2017DeLiGAN : Generative Adversarial Networks for Diverse and Limited Datacited by 77
  10. 2019Understanding Neural Networks via Feature Visualization: A surveycited by 65
  11. 2018Visualizing the Feature Importance for Black Box Modelscited by 55
  12. 2015Understanding Intra-Class Knowledge Inside CNNcited by 22
  13. 2016Rule Extraction Algorithm for Deep Neural Networks: A Reviewcited by 22
  14. 2021Surrogate Model-Based Explainability Methods for Point Cloud NNscited by 18
  15. 20203D Point Cloud Feature Explanations Using Gradient-Based Methodscited by 14
  16. 2020Explaining Clinical Decision Support Systems in Medical Imaging using Cycle-Consistent Activation Maximizationcited by 9
  17. 2019Gradient-free activation maximization for identifying effective stimulicited by 6
  18. 2019GAN-based Generation and Automatic Selection of Explanations for Neural Networkscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 2; 2026: 1.

8 papers.

  1. 2023Deep Learning Approaches for Seizure Video Analysis: A Reviewcited by 6
  2. 2024Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanationscited by 4
  3. 2024FFAM: Feature Factorization Activation Map for Explanation of 3D Detectorscited by 2
  4. 2025InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theorycited by 2
  5. 2024DAM: Diffusion Activation Maximization for 3D Global Explanationscited by 1
  6. 2024Flow AM: Generating Point Cloud Global Explanations by Latent Alignmentcited by 1
  7. 2025XAI for Point Cloud Data using Perturbations based on Meaningful Segmentationcited by 1
  8. 2026Synthetic LiDAR Data Generation and Deterministic Downsampling for Point Cloud Classification on the Edgecited by 0