Abstract
Explainable machine learning methods for point cloud analysis aim to decrease the model and computation complexity of current methods while improving their interpretation. These methods are an extension of successive subspace learning (SSL) from 2D images to 3D point clouds. SSL offers a lightweight unsupervised feature learning method based on the inherent statistical properties of data units. The model is significantly smaller than deep neural networks (DNNs) and more computationally efficient. However, it is nontrivial to generalize it to tackle the point cloud analysis problems, because points in a point cloud are irregular and unordered by nature, which is quite different from regular 2D images. In this chapter, we first discuss some early works on SSL processing of 2D images, then illustrate our explainable machine learning methods for point cloud classification, part segmentation, and registration in detail. Finally, we introduce some other applications of SSL .
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Representation learning and adversarial generation of 3d point clouds 2(3), 4 (2017). arXiv preprint arXiv:1707.02392
Aoki, Y., Goforth, H., Srivatsan, R.A., Lucey, S.: PointNetLK: Robust & efficient point cloud registration using PointNet. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7163–7172 (2019)
Besl, P.J., McKay, n.d.: Method for registration of 3-d shapes. In: Sensor Fusion IV: Control Paradigms and Data Structures, vol. 1611, pp. 586–606. International Society for Optics and Photonics (1992)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Chang, A.X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al.: ShapeNet: an information-rich 3d model repository (2015). arXiv preprint arXiv:1512.03012
Chen, H.S., Rouhsedaghat, M., Ghani, H., Hu, S., You, S., Kuo, C.C.J.: DefakeHop: a light-weight high-performance Deepfake detector. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6. IEEE (2021)
Chen, Y., Kuo, C.C.J.: PixelHop: A successive subspace learning (SSL) method for object recognition. J. Vis. Commun. Image Represent. 70, 102749 (2020)
Chen, Y., Rouhsedaghat, M., You, S., Rao, R., Kuo, C.C.J.: PixelHop+ +: a small successive-subspace-learning-based (SSL-based) model for image classification. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 3294–3298. IEEE (2020)
Chen, Y., Xu, Z., Cai, S., Lang, Y., Kuo, C.C.J.: A SaaK transform approach to efficient, scalable and robust handwritten digits recognition. In: 2018 Picture Coding Symposium (PCS), pp. 174–178. IEEE, Piscataway (2018)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Curless, B., Levoy, M.: A volumetric method for building complex models from range images. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, pp. 303–312 (1996)
Eldar, Y., Lindenbaum, M., Porat, M., Zeevi, Y.Y.: The farthest point strategy for progressive image sampling. IEEE Trans. Image Process. 6(9), 1305–1315 (1997)
Hassani, K., Haley, M.: Unsupervised multi-task feature learning on point clouds. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8160–8171 (2019)
Kadam, P., Zhang, M., Liu, S., Kuo, C.C.J.: Unsupervised point cloud registration via salient points analysis (SPA). In: 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), pp. 5–8. IEEE, Piscataway (2020)
Kadam, P., Zhang, M., Liu, S., Kuo, C.C.J.: R-PointHop: A green, accurate and unsupervised point cloud registration method (2021). arXiv preprint arXiv:2103.08129
Katsavounidis, I., Kuo, C.C.J., Zhang, Z.: A new initialization technique for generalized Lloyd iteration. IEEE Signal Process. Lett. 1(10), 144–146 (1994)
Krishnamurthy, V., Levoy, M.: Fitting smooth surfaces to dense polygon meshes. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, pp. 313–324 (1996)
Kuo, C.C.J.: Understanding convolutional neural networks with a mathematical model. J. Vis. Commun. Image Represent. 41, 406–413 (2016)
Kuo, C.C.J., Chen, Y.: On data-driven SaaK transform. J. Vis. Commun. Image Represent. 50, 237–246 (2018)
Kuo, C.C.J., Zhang, M., Li, S., Duan, J., Chen, Y.: Interpretable convolutional neural networks via feedforward design. J. Vis. Commun. Image Represent. 60, 346–359 (2019)
Li, J., Chen, B.M., Hee Lee, G.: So-net: Self-organizing network for point cloud analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9397–9406 (2018)
Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: Convolution on x-transformed points. In: Advances in Neural Information Processing Systems, pp. 820–830 (2018)
Lin, R., Zhou, Z., You, S., Rao, R., Kuo, C.C.J.: From two-class linear discriminant analysis to interpretable multilayer perceptron design (2020). arXiv preprint arXiv:2009.04442
Moenning, C., Dodgson, N.A.: Fast marching farthest point sampling. Tech. rep., University of Cambridge, Computer Laboratory (2003)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet+ +: Deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, pp. 5099–5108 (2017)
Rouhsedaghat, M., Monajatipoor, M., Azizi, Z., Kuo, C.C.J.: Successive subspace learning: an overview (2021). arXiv preprint arXiv:2103.00121
Rouhsedaghat, M., Wang, Y., Ge, X., Hu, S., You, S., Kuo, C.C.J.: FaceHop: a light-weight low-resolution face gender classification method (2020). arXiv preprint arXiv:2007.09510
Rouhsedaghat, M., Wang, Y., Ge, X., Hu, S., You, S., Kuo, C.C.J.: FaceHop: a light-weight low-resolution face gender classification method. In: International Conference on Pattern Recognition, pp. 169–183. Springer, Berlin (2021)
Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: Green AI (2019). arXiv preprint arXiv:1907.10597
Turk, G., Levoy, M.: Zippered polygon meshes from range images. In: Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, pp. 311–318 (1994)
Wagstaff, K., Cardie, C., Rogers, S., Schrödl, S., et al.: Constrained k-means clustering with background knowledge. In: ICML, vol. 1, pp. 577–584 (2001)
Wang, Y., Solomon, J.M.: Deep closest point: Learning representations for point cloud registration. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3523–3532 (2019)
Wang, Y., Solomon, J.M.: PRNeT: self-supervised learning for partial-to-partial registration (2019). arXiv preprint arXiv:1910.12240
Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds (2018). arXiv preprint arXiv:1801.07829
Wold, S., Esbensen, K., Geladi, P.: Principal component analysis. Chemom. Intell. Lab. Syst. 2(1–3), 37–52 (1987)
Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3D ShapeNets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912–1920 (2015)
Yang, J., Li, H., Campbell, D., Jia, Y.: Go-ICP: A globally optimal solution to 3D ICP point-set registration. IEEE Trans. Pattern Anal. Mach. Intell. 38(11), 2241–2254 (2015)
Yang, Y., Feng, C., Shen, Y., Tian, D.: FoldingNet: Point cloud auto-encoder via deep grid deformation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 206–215 (2018)
Yi, L., Kim, V.G., Ceylan, D., Shen, I., Yan, M., Su, H., Lu, C., Huang, Q., Sheffer, A., Guibas, L., et al.: A scalable active framework for region annotation in 3d shape collections. ACM Trans. Graph. 35(6), 210 (2016)
Zhang, K., Wang, B., Wang, W., Sohrab, F., Gabbouj, M., Kuo, C.C.J.: AnomalyHop: an SSL-based image anomaly localization method (2021). arXiv preprint arXiv:2105.03797
Zhang, M., Kadam, P., Liu, S., Kuo, C.C.J.: Unsupervised feedforward feature (UFF) learning for point cloud classification and segmentation. In: 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP), pp. 144–147. IEEE, Piscataway (2020)
Zhang, M., Wang, Y., Kadam, P., Liu, S., Kuo, C.C.J.: PointHop+ +: a lightweight learning model on point sets for 3d classification. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 3319–3323. IEEE, Piscataway (2020)
Zhang, M., You, H., Kadam, P., Liu, S., Kuo, C.C.J.: PointHop: An explainable machine learning method for point cloud classification. IEEE Trans. Multimedia 22(7), 1744–1755 (2020)
Zhao, Y., Birdal, T., Deng, H., Tombari, F.: 3D point capsule networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1009–1018 (2019)
Zhou, Q.Y., Park, J., Koltun, V.: Fast global registration. In: European Conference on Computer Vision, pp. 766–782. Springer, Berlin (2016)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Liu, S., Zhang, M., Kadam, P., Kuo, CC.J. (2021). Explainable Machine Learning Methods for Point Cloud Analysis. In: 3D Point Cloud Analysis. Springer, Cham. https://doi.org/10.1007/978-3-030-89180-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-89180-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89179-4
Online ISBN: 978-3-030-89180-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)