RST: Rough Set Transformer for Point Cloud Learning
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 outstan...
| Hoofdauteurs: | , |
|---|---|
| Formaat: | Artikel |
| Taal: | English |
| Gepubliceerd in: |
MDPI AG
2023-11-01
|
| Reeks: | Sensors |
| Onderwerpen: | |
| Online toegang: | https://www.mdpi.com/1424-8220/23/22/9042 |
| _version_ | 1827638811653308416 |
|---|---|
| author | Xinwei Sun Kai Zeng |
| author_facet | Xinwei Sun Kai Zeng |
| author_sort | Xinwei Sun |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T16:28:06Z |
| format | Article |
| id | doaj.art-0efd44d14c944e4ab04b9fdeff88b0be |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T16:28:06Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0efd44d14c944e4ab04b9fdeff88b0be2023-11-24T15:05:07ZengMDPI AGSensors1424-82202023-11-012322904210.3390/s23229042RST: Rough Set Transformer for Point Cloud LearningXinwei Sun0Kai Zeng1Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaPoint 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.https://www.mdpi.com/1424-8220/23/22/90423D sensorsrough settransformerpoint cloud learning |
| spellingShingle | Xinwei Sun Kai Zeng RST: Rough Set Transformer for Point Cloud Learning Sensors 3D sensors rough set transformer point cloud learning |
| title | RST: Rough Set Transformer for Point Cloud Learning |
| title_full | RST: Rough Set Transformer for Point Cloud Learning |
| title_fullStr | RST: Rough Set Transformer for Point Cloud Learning |
| title_full_unstemmed | RST: Rough Set Transformer for Point Cloud Learning |
| title_short | RST: Rough Set Transformer for Point Cloud Learning |
| title_sort | rst rough set transformer for point cloud learning |
| topic | 3D sensors rough set transformer point cloud learning |
| url | https://www.mdpi.com/1424-8220/23/22/9042 |
| work_keys_str_mv | AT xinweisun rstroughsettransformerforpointcloudlearning AT kaizeng rstroughsettransformerforpointcloudlearning |