mlsanityData to 7 Oct 2026

Surrogate Model-Based Explainability Methods for Point Cloud NNs

arXiv 2107.13459 ↗First posted 28 Jul 2021cs.CV cs.LGcited by 18

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 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 18 papers in the map (data through 7 Oct 2026). Builds on 29 of its 42 references that are in the map. First posted on arXiv 28 Jul 2021.

Builds on

29 of 42 references.

References · 29

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  9. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  10. 2018Sanity Checks for Saliency Mapscited by 1,149
  11. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  12. 2017SmoothGrad: removing noise by adding noisecited by 1,097
17 more
  1. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  2. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  3. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  4. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  5. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
  6. 2018PointCloud Saliency Mapscited by 112
  7. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  8. 2019Understanding Neural Networks via Feature Visualization: A surveycited by 65
  9. 2019PointHop: An Explainable Machine Learning Method for Point Cloud Classificationcited by 46
  10. 2019Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Mapscited by 34
  11. 2016Gradients of Counterfactualscited by 31
  12. 2016Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modelingcited by 28
  13. 2020Explaining Autonomous Driving by Learning End-to-End Visual Attentioncited by 25
  14. 2019Deep neural network or dermatologist?cited by 20
  15. 20203D Point Cloud Feature Explanations Using Gradient-Based Methodscited by 14
  16. 2020Study of Different Deep Learning Approach with Explainable AI for Screening Patients with COVID-19 Symptoms: Using CT Scan and Chest X-ray Image Datasetcited by 7
  17. 2020Evaluating the performance of the LIME and Grad-CAM explanation methods on a LEGO multi-label image classification taskcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 1; 2024: 7; 2025: 4; 2026: 2.

18 papers.

Sort:

By area:

  1. 2024Contestable AI needs Computational Argumentationcited by 12
  2. 2022Visualizing Global Explanations of Point Cloud DNNscited by 8
  3. 2021Explainability-Aware One Point Attack for Point Cloud Neural Networkscited by 7
  4. 2024Fast and Simple Explainability for Point Cloud Networkscited by 6
  5. 2024Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanationscited by 4
  6. 2022Maximum Entropy Baseline for Integrated Gradientscited by 3
  7. 2024One Wave To Explain Them All: A Unifying Perspective On Feature Attributioncited by 3
  8. 2022Concept Activation Vectors for Generating User-Defined 3D Shapescited by 2
  9. 2023Robustifying Point Cloud Networks by Refocusingcited by 2
  10. 2025InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theorycited by 2
  11. 2024DAM: Diffusion Activation Maximization for 3D Global Explanationscited by 1
  12. 2024Flow AM: Generating Point Cloud Global Explanations by Latent Alignmentcited by 1
6 more
  1. 2025Explainable LiDAR 3D Point Cloud Segmentation and Clustering for Detecting Airplane-Generated Wind Turbulencecited by 1
  2. 2025XAI for Point Cloud Data using Perturbations based on Meaningful Segmentationcited by 1
  3. 2024Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Propertycited by 0
  4. 2025PointExplainer: Towards Transparent Parkinson's Disease Diagnosiscited by 0
  5. 2026XSPLAIN: XAI-enabling Splat-based Prototype Learning for Attribute-aware INterpretabilitycited by 0
  6. 2026Synthetic LiDAR Data Generation and Deterministic Downsampling for Point Cloud Classification on the Edgecited by 0