Papers
Topics
Authors
Recent
Search
2000 character limit reached

3D Point Cloud Network Pruning: When Some Weights Do not Matter

Published 26 Aug 2024 in cs.CV | (2408.14601v1)

Abstract: A point cloud is a crucial geometric data structure utilized in numerous applications. The adoption of deep neural networks referred to as Point Cloud Neural Networks (PC- NNs), for processing 3D point clouds, has significantly advanced fields that rely on 3D geometric data to enhance the efficiency of tasks. Expanding the size of both neural network models and 3D point clouds introduces significant challenges in minimizing computational and memory requirements. This is essential for meeting the demanding requirements of real-world applications, which prioritize minimal energy consumption and low latency. Therefore, investigating redundancy in PCNNs is crucial yet challenging due to their sensitivity to parameters. Additionally, traditional pruning methods face difficulties as these networks rely heavily on weights and points. Nonetheless, our research reveals a promising phenomenon that could refine standard PCNN pruning techniques. Our findings suggest that preserving only the top p% of the highest magnitude weights is crucial for accuracy preservation. For example, pruning 99% of the weights from the PointNet model still results in accuracy close to the base level. Specifically, in the ModelNet40 dataset, where the base accuracy with the PointNet model was 87. 5%, preserving only 1% of the weights still achieves an accuracy of 86.8%. Codes are available in: https://github.com/apurba-nsu-rnd-lab/PCNN_Pruning

Definition Search Book Streamline Icon: https://streamlinehq.com
References (70)
  1. Deepismnet: Three-dimensional implicit structural modeling with convolutional neural network. Geoscientific Model Development, 15(17):6841–6861, 2022.
  2. What is the state of neural network pruning? Proceedings of machine learning and systems, 2:129–146, 2020.
  3. Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine, 34(4):18–42, 2017.
  4. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012, 2015.
  5. The lottery tickets hypothesis for supervised and self-supervised pre-training in computer vision models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16306–16316, 2021a.
  6. Only train once: A one-shot neural network training and pruning framework. Advances in Neural Information Processing Systems, 34:19637–19651, 2021b.
  7. The elastic lottery ticket hypothesis. Advances in Neural Information Processing Systems, 34:26609–26621, 2021c.
  8. Mitigating the hubness problem for zero-shot learning of 3d objects. In British Machine Vision Conference (BMVC), 2019.
  9. Studying the impact of magnitude pruning on contrastive learning methods. arXiv preprint arXiv:2207.00200, 2022.
  10. Learning so (3) equivariant representations with spherical cnns. In Proceedings of the European Conference on Computer Vision (ECCV), pages 52–68, 2018.
  11. 3dac: Learning attribute compression for point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14819–14828, 2022.
  12. The lottery ticket hypothesis: Finding sparse, trainable neural networks. In International Conference on Learning Representations, 2018.
  13. Stabilizing the lottery ticket hypothesis. arXiv preprint arXiv:1903.01611, 2019.
  14. Linear mode connectivity and the lottery ticket hypothesis. In International Conference on Machine Learning, pages 3259–3269. PMLR, 2020.
  15. Playing lottery tickets with vision and language. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 652–660, 2022.
  16. A survey of traditional and deep learning-based feature descriptors for high dimensional data in computer vision. International Journal of Multimedia Information Retrieval, 9:135–170, 2020.
  17. The lottery ticket hypothesis for object recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 762–771, 2021.
  18. Regularization theory and neural networks architectures. Neural computation, 7(2):219–269, 1995.
  19. Revisiting point cloud shape classification with a simple and effective baseline. In International Conference on Machine Learning, pages 3809–3820. PMLR, 2021.
  20. To supervise or not to supervise: Understanding and addressing the key challenges of 3d transfer learning. arXiv preprint arXiv:2403.17869, 2024.
  21. Victor Petrén Bach Hansen and Anders Søgaard. Is the lottery fair? evaluating winning tickets across demographics. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3214–3224, 2021.
  22. Transferring lottery tickets in computer vision models: a dynamic pruning approach. In 2023 IEEE International Conference on Big Data (BigData), pages 1123–1128. IEEE, 2023.
  23. Three-dimensional structural geological modeling using graph neural networks. Mathematical geosciences, 53(8):1725–1749, 2021.
  24. Colt: Cyclic overlapping lottery tickets for faster pruning of convolutional neural networks. arXiv preprint arXiv:2212.12770, 2022.
  25. Channel gating neural networks. Advances in Neural Information Processing Systems, 32, 2019.
  26. Cp3: Channel pruning plug-in for point-based networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5302–5312, 2023.
  27. How well do sparse imagenet models transfer? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12266–12276, 2022.
  28. Instant soup: Cheap pruning ensembles in a single pass can draw lottery tickets from large models. In International Conference on Machine Learning, pages 14691–14701. PMLR, 2023.
  29. Rotation-invariant local-to-global representation learning for 3d point cloud. Advances in Neural Information Processing Systems, 33:8174–8185, 2020.
  30. Not all neighbors matter: point distribution-aware pruning for 3d point cloud. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 1240–1249, 2023.
  31. Mseg3d: Multi-modal 3d semantic segmentation for autonomous driving. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 21694–21704, 2023.
  32. Pointcnn: Convolution on x-transformed points. Advances in neural information processing systems, 31, 2018.
  33. Can unstructured pruning reduce the depth in deep neural networks? In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1402–1406, 2023.
  34. Path planning techniques for mobile robots: Review and prospect. Expert Systems with Applications, page 120254, 2023.
  35. Densepoint: Learning densely contextual representation for efficient point cloud processing. In Proceedings of the IEEE/CVF international conference on computer vision, pages 5239–5248, 2019.
  36. Proving the lottery ticket hypothesis: Pruning is all you need. In International Conference on Machine Learning, pages 6682–6691. PMLR, 2020.
  37. Def: Deep estimation of sharp geometric features in 3d shapes. ACM Transactions on Graphics, 41(4), 2022.
  38. Contrastive dual gating: Learning sparse features with contrastive learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12257–12265, 2022.
  39. Structure-aware shape processing. In ACM SIGGRAPH 2014 Courses, pages 1–21. 2014.
  40. Ric-cnn: Rotation-invariant coordinate convolutional neural network. Pattern Recognition, 146:109994, 2024.
  41. One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers. Advances in neural information processing systems, 32, 2019.
  42. Lossless point cloud geometry and attribute compression using a learned conditional probability model. IEEE Transactions on Circuits and Systems for Video Technology, 33(8):4337–4348, 2023.
  43. Shape-driven deep neural networks for fast acquisition of aortic 3d pressure and velocity flow fields. PLoS Computational Biology, 19(4):e1011055, 2023.
  44. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, 2017.
  45. Octnet: Learning deep 3d representations at high resolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3577–3586, 2017.
  46. Distributionally robust ensemble of lottery tickets towards calibrated sparse network training. Advances in Neural Information Processing Systems, 36, 2024.
  47. Mining point cloud local structures by kernel correlation and graph pooling. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4548–4557, 2018.
  48. Dynamic local geometry capture in 3d point cloud classification. In 2021 IEEE 4th international conference on multimedia information processing and retrieval (MIPR), pages 158–164. IEEE, 2021.
  49. Multi-view convolutional neural networks for 3d shape recognition. In Proceedings of the IEEE international conference on computer vision, pages 945–953, 2015.
  50. Structured prediction of 3d human pose with deep neural networks. arXiv preprint arXiv:1605.05180, 2016.
  51. High dimensional neural networks and applications. In Intelligent autonomous systems: foundations and applications, pages 215–233. Springer, 2010.
  52. Views on augmented reality, virtual reality, and 3d printing in modern medicine and education: A qualitative exploration of expert opinion. Journal of Digital Imaging, 36(4):1930–1939, 2023.
  53. Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data. In International Conference on Computer Vision (ICCV), 2019.
  54. A survey on deep learning based segmentation, detection and classification for 3d point clouds. Entropy, 25(4):635, 2023.
  55. Lossy point cloud geometry compression via end-to-end learning. IEEE Transactions on Circuits and Systems for Video Technology, 31(12):4909–4923, 2021.
  56. O-cnn: Octree-based convolutional neural networks for 3d shape analysis. ACM Transactions On Graphics (TOG), 36(4):1–11, 2017.
  57. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (tog), 38(5):1–12, 2019.
  58. Geometric features and their relevance for 3d point cloud classification. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 4:157–164, 2017.
  59. Pointconv: Deep convolutional networks on 3d point clouds. In Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition, pages 9621–9630, 2019.
  60. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1912–1920, 2015.
  61. Quantization networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7308–7316, 2019.
  62. Easiedge: A novel global deep neural networks pruning method for efficient edge computing. IEEE Internet of Things Journal, 8(3):1259–1271, 2020.
  63. Pointclip: Point cloud understanding by clip. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8552–8562, 2022a.
  64. Parameter is not all you need: Starting from non-parametric networks for 3d point cloud analysis. arXiv preprint arXiv:2303.08134, 2023.
  65. Advancing model pruning via bi-level optimization. Advances in Neural Information Processing Systems, 35:18309–18326, 2022b.
  66. Deconstructing lottery tickets: Zeros, signs, and the supermask. Advances in neural information processing systems, 32, 2019a.
  67. Uni3d: Exploring unified 3d representation at scale. arXiv preprint arXiv:2310.06773, 2023.
  68. Distilling holistic knowledge with graph neural networks. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10387–10396, 2021.
  69. On the continuity of rotation representations in neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5745–5753, 2019b.
  70. Voxelnet: End-to-end learning for point cloud based 3d object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4490–4499, 2018.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

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

Continue Learning

We haven't generated follow-up questions for this paper yet.

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

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up