Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification (2307.10875v3)

Published 20 Jul 2023 in cs.CV, cs.CR, and cs.LG

Abstract: With the growth of 3D sensing technology, deep learning system for 3D point clouds has become increasingly important, especially in applications like autonomous vehicles where safety is a primary concern. However, there are also growing concerns about the reliability of these systems when they encounter noisy point clouds, whether occurring naturally or introduced with malicious intent. This paper highlights the challenges of point cloud classification posed by various forms of noise, from simple background noise to malicious backdoor attacks that can intentionally skew model predictions. While there's an urgent need for optimized point cloud denoising, current point outlier removal approaches, an essential step for denoising, rely heavily on handcrafted strategies and are not adapted for higher-level tasks, such as classification. To address this issue, we introduce an innovative point outlier cleansing method that harnesses the power of downstream classification models. By employing gradient-based attribution analysis, we define a novel concept: point risk. Drawing inspiration from tail risk minimization in finance, we recast the outlier removal process as an optimization problem, named PointCVaR. Extensive experiments show that our proposed technique not only robustly filters diverse point cloud outliers but also consistently and significantly enhances existing robust methods for point cloud classification.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Coherent measures of risk. Mathematical finance, 9(3): 203–228.
  2. ShapeNet: An Information-Rich 3D Model Repository. Technical Report arXiv:1512.03012 [cs.GR], Stanford University — Princeton University — Toyota Technological Institute at Chicago.
  3. Multi-view 3d object detection network for autonomous driving. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1907–1915.
  4. Pointmixup: Augmentation for point clouds. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16, 330–345. Springer.
  5. Self-robust 3d point recognition via gather-vector guidance. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 11513–11521. IEEE.
  6. Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline. International Conference on Machine Learning.
  7. Pct: Point cloud transformer. Computational Visual Media, 7: 187–199.
  8. Advpc: Transferable adversarial perturbations on 3d point clouds. In European Conference on Computer Vision, 241–257. Springer.
  9. Shape-invariant 3d adversarial point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 15335–15344.
  10. Karmarkar, N. 1984. A new polynomial-time algorithm for linear programming. In Proceedings of the sixteenth annual ACM symposium on Theory of computing, 302–311.
  11. Pointba: Towards backdoor attacks in 3d point cloud. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 16492–16501.
  12. Adversarial examples detection in deep networks with convolutional filter statistics. In Proceedings of the IEEE international conference on computer vision, 5764–5772.
  13. Defense against adversarial attacks using high-level representation guided denoiser. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1778–1787.
  14. Defensive quantization: When efficiency meets robustness. In International Conference on Learning Representations. International Conference on Learning Representations, ICLR.
  15. Extending adversarial attacks and defenses to deep 3d point cloud classifiers. In 2019 IEEE International Conference on Image Processing (ICIP), 2279–2283. IEEE.
  16. Pointguard: Provably robust 3d point cloud classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6186–6195.
  17. Pflug, G. C. 2000. Some remarks on the value-at-risk and the conditional value-at-risk. Probabilistic constrained optimization: Methodology and applications, 272–281.
  18. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 652–660.
  19. Pointcleannet: Learning to denoise and remove outliers from dense point clouds. In Computer graphics forum. Wiley Online Library.
  20. Benchmarking and analyzing point cloud classification under corruptions. In International Conference on Machine Learning, 18559–18575. PMLR.
  21. Optimization of conditional value-at-risk. Journal of risk, 2: 21–42.
  22. Rusu, R. B. 2010. Semantic 3D object maps for everyday manipulation in human living environments. KI-Künstliche Intelligenz, 24: 345–348.
  23. 3d is here: Point cloud library (pcl). In 2011 IEEE international conference on robotics and automation, 1–4. IEEE.
  24. Interpreting representation quality of dnns for 3d point cloud processing. Advances in Neural Information Processing Systems, 34: 8857–8870.
  25. Learning important features through propagating activation differences. In International conference on machine learning, 3145–3153. PMLR.
  26. Deep inside convolutional networks: visualising image classification models and saliency maps. In Proceedings of the International Conference on Learning Representations (ICLR). ICLR.
  27. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825.
  28. Striving for Simplicity: The All Convolutional Net. In ICLR (workshop track).
  29. Adversarially robust 3d point cloud recognition using self-supervisions. Advances in Neural Information Processing Systems, 34: 15498–15512.
  30. On adversarial robustness of 3d point cloud classification under adaptive attacks. arXiv preprint arXiv:2011.11922.
  31. Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions. arXiv preprint arXiv:2201.12296.
  32. Axiomatic attribution for deep networks. In International conference on machine learning, 3319–3328. PMLR.
  33. Robust adversarial objects against deep learning models. In Proceedings of the AAAI Conference on Artificial Intelligence, 954–962.
  34. Physically Realizable Adversarial Examples for LiDAR Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13716–13725.
  35. Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. In Proceedings of the IEEE/CVF international conference on computer vision, 1588–1597.
  36. Dynamic graph cnn for learning on point clouds. Acm Transactions On Graphics (tog), 38(5): 1–12.
  37. Robustness of 3d deep learning in an adversarial setting. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 11767–11775.
  38. If-defense: 3d adversarial point cloud defense via implicit function based restoration. arXiv preprint arXiv:2010.05272.
  39. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1912–1920.
  40. Generating 3d adversarial point clouds. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 9136–9144.
  41. A backdoor attack against 3d point cloud classifiers. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 7597–7607.
  42. Learning geometry-disentangled representation for complementary understanding of 3d object point cloud. In Proceedings of the AAAI conference on artificial intelligence, 3056–3064.
  43. Adversarial attack and defense on point sets. arXiv preprint arXiv:1902.10899.
  44. Pointcutmix: Regularization strategy for point cloud classification. Neurocomputing, 505: 58–67.
  45. On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attacks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1201–1210.
  46. Pointcloud saliency maps. In Proceedings of the IEEE International Conference on Computer Vision, 1598–1606.
  47. DUP-Net: Denoiser and upsampler network for 3D adversarial point clouds defense. In Proceedings of the IEEE International Conference on Computer Vision, 1961–1970.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now