Abstract
Applying deep learning techniques to analyze point cloud data has emerged as a prominent research direction. However, the insufficient spatial and feature information integration within point cloud and unbalanced classes in real-world datasets have hindered the advancement of research. Given the success of self-attention mechanisms in numerous domains, we apply the High-Resolution Self-Attention (HRSA) module as a plug-and-play solution for point cloud segmentation. The proposed HRSA module preserve high-resolution internal representations in both spatial and feature dimensions. Additionally, by affecting the gradient of dominant and weak classes, we introduce the Fair Loss to address the problem of unbalanced class distribution on a real-world dataset to improve the network’s inference capabilities. The introduced modules are seamlessly integrated into an MLP-based architecture tailored for large-scale point cloud processing, resulting in a new segmentation network called PointHR. PointHR achieves impressive performance with mIoU scores of 69.8% and 74.5% on S3DIS Area-5 and 6-fold cross-validation. With a significantly smaller number of parameters, these performances make PointHR highly competitive in point cloud semantic segmentation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Change history
15 December 2023
A correction has been published.
References
Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L., Bennamoun, M.: Deep learning for 3D point clouds: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43(12), 4338–4364 (2021)
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 Computer Vision Pattern Recognition (CVPR), vol. 1, p. 4 (2017)
Qian, G., et al.: PointNeXt: revisiting PointNet++ with improved training and scaling strategies(2022). arXiv:2206.04670
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)
Zhao, H., Jiang, L., Fu, C.W., Jia, J.: Pointweb: enhancing local neighborhood features for point cloud processing. In: Proeedings of the IEEE Conference Computer Vision Pattern Recognition (CVPR), pp. 5565–5573 (2019)
Zhang, Y., Hu, Q., Xu, G., Ma, Y., Wan, J., Guo, Y.: Not all points are equal: learning highly efficient point-based detectors for 3D LiDAR point clouds. In: IEEE/CVF Conference Computer Vision Pattern Recognition (CVPR), New Orleans, LA, USA, 2022, pp. 18931–18940 (2022)
Hu, Q., et al.: RandLA-net: efficient semantic segmentation of large-scale point clouds. In: Proceedings of IEEE/CVF Conference Computer Vision Pattern Recognition (CVPR), pp. 11108–11117 (2020)
Guo, M.-H., et al.: Point cloud transformer. Comput. Vis. Media 7(2), 187–199 (2021)
Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V., et al.: Point transformer. In: Proceedings International Conference Computer Vision, pp. 16259–16268 (2021)
Lai, X., et al.: Stratified transformer for 3D point cloud segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (CVPR), pp. 8500–8509 (2022)
Armeni, I., et al.: 3D semantic parsing of large-scale indoor spaces. In: Proceedings IEEE Conerence Computer Vision Pattern Recognition, pp. 1534–1543 (2016)
Boulch, A., Guerry, J., Le Saux, B., Audebert, N.: SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networks. Comput. Graph. 71, 189–198 (2018)
Wu, B., Wan, A., Yue, X., Keutzer, K.: SqueezeSeg: convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR point cloud. In: Proceedings IEEE International Conference on Robotics Automation (ICRA), Brisbane, QLD, Australia, 2018, pp. 1887–1893 (2018)
Wu, B., Zhou, X., Zhao, S., Yue, X., Keutzer, K.: SqueezeSegV2: improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud. In: Proceedings IEEE International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 2019, pp. 4376–4382 (2019)
Tchapmi, L., Choy, C., Armeni, I., Gwak, J., Savarese, S.: SEGCloud: semantic segmentation of 3d point clouds. In: Proceedings Inernational Conference 3D Vision (3DV), Qingdao, China, 2017, pp. 537–547 (2017)
Liu, Z., Tang, H., Lin, Y., Han, S.: Point-voxel CNN for efficient 3D deep learning. In: Advances in Neural Information Processing Systems, Cambridge, MA, USA:MIT Press, 2019, pp. 965–975 (2019)
Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference Neural Information Processing System, pp. 5998–6008 (2017)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Paszke, A., et al.: PyTorch: an imperative style high-performance deep learning library. In: Proceedings Advance Neural Information Processing System, pp. 8026–8037 (2019)
Lin, Y., et al.: PointCNN: Convolution on \(\chi \) -transformed points. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 826–836 (2018)
Yang, J., et al.: Modeling point clouds with self-attention and gumbel subset sampling. In: Proceedings of the IEEE/CVF Conference Computer Vision Pattern Recognition, pp. 3323–3332 (2019)
Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and Deformable Convolution for Point Clouds. In: Proceedings of IEEE International Conference Computer Vision (ICCV), 2019, pp. 6411–6420 (2019)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference Computer Vision Pattern Recognition, pp. 2818–2826. (2016)
Acknowledgement
This work was supported in part by the Heilongjiang Provincial Science and Technology Program under Grant 2022ZX01A16, and in part by the Sichuan Science and Technology Program under Grant 2022YFG0148.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Q., Lu, J., Li, Q., Huang, B. (2024). High-Resolution Self-attention with Fair Loss for Point Cloud Segmentation. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Lecture Notes in Computer Science, vol 14451. Springer, Singapore. https://doi.org/10.1007/978-981-99-8073-4_27
Download citation
DOI: https://doi.org/10.1007/978-981-99-8073-4_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8072-7
Online ISBN: 978-981-99-8073-4
eBook Packages: Computer ScienceComputer Science (R0)