mlsanityData to 7 Oct 2026

DAM: Diffusion Activation Maximization for 3D Global Explanations

arXiv 2401.14938 ↗First posted 26 Jan 2024cs.CVcited by 1

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

In recent years, the performance of point cloud models has been rapidly improved. However, due to the limited amount of relevant explainability studies, the unreliability and opacity of these black-box models may lead to potential risks in applications where human lives are at stake, e.g. autonomous driving or healthcare. This work proposes a DDPM-based point cloud global explainability method (DAM) that leverages Point Diffusion Transformer (PDT), a novel point-wise symmetric model, with dual-classifier guidance to generate high-quality global explanations. In addition, an adapted path gradient integration method for DAM is proposed, which not only provides a global overview of the saliency maps for point cloud categories, but also sheds light on how the attributions of the explanations vary during the generation process. Extensive experiments indicate that our method outperforms existing ones in terms of perceptibility, representativeness, and diversity, with a significant reduction in generation time. Our code is available at: https://github.com/Explain3D/DAM

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 47 of its 63 references that are in the map. First posted on arXiv 26 Jan 2024.

Builds on

47 of 63 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  2. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion7 Dec
  3. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 44

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  10. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  11. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  12. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
32 more
  1. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  2. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  3. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  4. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  5. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  6. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  7. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  8. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  9. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  10. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  11. 2018On the Robustness of Interpretability Methodscited by 310
  12. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  13. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
  14. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
  15. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  16. 2016Synthesizing the preferred inputs for neurons in neural networks via deep generator networkscited by 181
  17. 2020Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Reviewcited by 174
  18. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  19. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  20. 2018PointCloud Saliency Mapscited by 112
  21. 2020Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Reviewcited by 107
  22. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  23. 2019A-CNN: Annularly Convolutional Neural Networks on Point Cloudscited by 66
  24. 2020Evaluations and Methods for Explanation through Robustness Analysiscited by 51
  25. 2018Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNNcited by 33
  26. 2016Rule Extraction Algorithm for Deep Neural Networks: A Reviewcited by 22
  27. 2021Surrogate Model-Based Explainability Methods for Point Cloud NNscited by 18
  28. 20203D Point Cloud Feature Explanations Using Gradient-Based Methodscited by 14
  29. 2020A Learning Theoretic Perspective on Local Explainabilitycited by 11
  30. 2022Visualizing Global Explanations of Point Cloud DNNscited by 8
  31. 2021Explainability-Aware One Point Attack for Point Cloud Neural Networkscited by 7
  32. 2018Rule induction for global explanation of trained modelscited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanationscited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2024PointInfinity: Resolution-Invariant Point Diffusion Models
  2. 2023Point Cloud Pre-training with Diffusion Models
  3. 2025Guided and Unguided Conditional Diffusion Mechanisms for Structured and Semantically-Aware 3D Point Cloud Generation
  4. 2025PDT: Point Distribution Transformation with Diffusion Models
  5. 2026PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning
  6. 2025SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation
  7. 2025SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation
  8. 2026Diffusion Masked Pretraining for Dynamic Point Cloud