RST: Rough Set Transformer for Point Cloud Learning
Affiliation:
1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
Abstract
Point cloud data generated by LiDAR sensors play a critical role in 3D sensing systems, with applications encompassing object classification, part segmentation, and point cloud recognition. Leveraging the global learning capacity of dot product attention, transformers have recently exhibited outstanding performance in point cloud learning tasks. Nevertheless, existing transformer models inadequately address the challenges posed by uncertainty features in point clouds, which can introduce errors in the dot product attention mechanism. In response to this, our study introduces a novel global guidance approach to tolerate uncertainty and provide a more reliable guidance. We redefine the granulation and lower-approximation operators based on neighborhood rough set theory. Furthermore, we introduce a rough set-based attention mechanism tailored for point cloud data and present the rough set transformer (RST) network. Our approach utilizes granulation concepts derived from token clusters, enabling us to explore relationships between concepts from an approximation perspective, rather than relying on specific dot product functions. Empirically, our work represents the pioneering fusion of rough set theory and transformer networks for point cloud learning. Our experimental results, including point cloud classification and segmentation tasks, demonstrate the superior performance of our method. Our method establishes concepts based on granulation generated from clusters of tokens. Subsequently, relationships between concepts can be explored from an approximation perspective, instead of relying on specific dot product or addition functions. Empirically, our work represents the pioneering fusion of rough set theory and transformer networks for point cloud learning. Our experimental results, including point cloud classification and segmentation tasks, demonstrate the superior performance of our method.
Funder
Major Science and Technology Projects in Yunnan Province Yunnan Fundamental Research Projects Kunming University of Science and Technology
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference38 articles.
1. Wang, Y., Zuo, Y., Du, Z., Song, X., Luo, T., Hong, X., and Wu, J. (2023). MInet: A Novel Network Model for Point Cloud Processing by Integrating Multi-Modal Information. Sensors, 23. 2. Villa, F., Severini, F., Madonini, F., and Zappa, F. (2021). SPADs and SiPMs arrays for long-range high-speed light detection and ranging(LiDAR). Sensors, 21. 3. Point clouds learning with attention-based graph convolution networks;Xie;Neurocomputing,2020 4. Li, Y., Bu, R., Sun, M., Wu, W., Di, X., and Chen, B. (2018, January 3–8). Pointcnn: Convolution on x-transformed points. Proceedings of the Annual Conference on Neural Information Processing Systems, Montréal, QC, Canada. 5. Point Convolutional Neural Networks by Extension Operators;Atzmon;ACM Trans. Graph.,2018
|
|