mlsanityData to 14 Oct 2026

PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition

arXiv 2209.07788 ↗First posted 16 Sep 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Notwithstanding the prominent performance achieved in various applications, point cloud recognition models have often suffered from natural corruptions and adversarial perturbations. In this paper, we delve into boosting the general robustness of point cloud recognition models and propose Point-Cloud Contrastive Adversarial Training (PointCAT). The main intuition of PointCAT is encouraging the target recognition model to narrow the decision gap between clean point clouds and corrupted point clouds. Specifically, we leverage a supervised contrastive loss to facilitate the alignment and uniformity of the hypersphere features extracted by the recognition model, and design a pair of centralizing losses with the dynamic prototype guidance to avoid these features deviating from their belonging category clusters. To provide the more challenging corrupted point clouds, we adversarially train a noise generator along with the recognition model from the scratch, instead of using gradient-based attack as the inner loop like previous adversarial training methods. Comprehensive experiments show that the proposed PointCAT outperforms the baseline methods and dramatically boosts the robustness of different point cloud recognition models, under a variety of corruptions including isotropic point noises, the LiDAR simulated noises, random point dropping and adversarial perturbations.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 59 of its 79 references that are in the map. First posted on arXiv 16 Sep 2022.

Builds on

59 of 79 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2013Intriguing properties of neural networkscited by 5,155
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  10. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  11. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  12. 2020Supervised Contrastive Learningcited by 2,829
38 more
  1. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  2. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  3. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  5. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  6. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  7. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  8. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  9. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
  10. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  11. 2019On Mutual Information Maximization for Representation Learningcited by 316
  12. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  13. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  14. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  15. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  16. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  17. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 152
  18. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  19. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  20. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  21. 2018Generating 3D Adversarial Point Cloudscited by 144
  22. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  23. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 140
  24. 2020Adversarial Self-Supervised Contrastive Learningcited by 139
  25. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  26. 2020PointMixup: Augmentation for Point Cloudscited by 104
  27. 2021Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attackscited by 101
  28. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  29. 2019NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networkscited by 94
  30. 2020Learnable Boundary Guided Adversarial Trainingcited by 93
  31. 2019AdvPC: Transferable Adversarial Perturbations on 3D Point Cloudscited by 84
  32. 2022Surface Representation for Point Cloudscited by 84
  33. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 80
  34. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 77
  35. 2019Training Robust Deep Neural Networks via Adversarial Noise Propagationcited by 62
  36. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  37. 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
  38. 2020Differentiable Manifold Reconstruction for Point Cloud Denoisingcited by 52

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

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

10 papers.

  1. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  2. 2023SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Modelscited by 36
  3. 2024Adversarial Training: A Surveycited by 6
  4. 2024COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attackscited by 2
  5. 2024Rethinking Attention Module Design for Point Cloud Analysiscited by 2
  6. 2024Improving Fast Adversarial Training via Self-Knowledge Guidancecited by 2
  7. 2023MOVES: Movable and Moving LiDAR Scene Segmentation in Label-Free settings using Static Reconstructioncited by 1
  8. 2025Skeleton-based Robust Registration Framework for Corrupted 3D Point Cloudscited by 0
  9. 2026PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Waveletscited by 0
  10. 2026Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustnesscited by 0