Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification
Understanding the implication of point cloud is still challenging in the aim of classification or segmentation for point cloud due to its irregular and sparse structure. As we have known, PointNet architecture as a ground-breaking work for point cloud process can learn shape features directly on uno...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/8832081 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560091372453888 |
|---|---|
| author | Xi-An Li Li-Yan Wang Jian Lu |
| author_facet | Xi-An Li Li-Yan Wang Jian Lu |
| author_sort | Xi-An Li |
| collection | DOAJ |
| description | Understanding the implication of point cloud is still challenging in the aim of classification or segmentation for point cloud due to its irregular and sparse structure. As we have known, PointNet architecture as a ground-breaking work for point cloud process can learn shape features directly on unordered 3D point cloud and has achieved favorable performance, such as 86% mean accuracy and 89.2% overall accuracy for classification task, respectively. However, this model fails to consider the fine-grained semantic information of local structure for point cloud. Then, a multiscale receptive fields graph attention network (named after MRFGAT) by means of semantic features of local patch for point cloud is proposed in this paper, and the learned feature map for our network can well capture the abundant features information of point cloud. The proposed MRFGAT architecture is tested on ModelNet datasets, and results show it achieves state-of-the-art performance in shape classification tasks, such as it outperforms GAPNet (Chen et al.) model by 0.1% in terms of OA and compete with DGCNN (Wang et al.) model in terms of MA. |
| format | Article |
| id | doaj-art-1bafdf0e24c946e0b5e0ab24f529fc6e |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-1bafdf0e24c946e0b5e0ab24f529fc6e2025-02-03T01:28:25ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/88320818832081Multiscale Receptive Fields Graph Attention Network for Point Cloud ClassificationXi-An Li0Li-Yan Wang1Jian Lu2Department of Stomatology, Foshan Woman and Children’s Hospital, Foshan, Guangdong 528000, ChinaDepartment of Stomatology, Foshan Woman and Children’s Hospital, Foshan, Guangdong 528000, ChinaGuangdong Institute of Aeronautics and Astronautics Equipment and Technology, Zhuhai 519000, ChinaUnderstanding the implication of point cloud is still challenging in the aim of classification or segmentation for point cloud due to its irregular and sparse structure. As we have known, PointNet architecture as a ground-breaking work for point cloud process can learn shape features directly on unordered 3D point cloud and has achieved favorable performance, such as 86% mean accuracy and 89.2% overall accuracy for classification task, respectively. However, this model fails to consider the fine-grained semantic information of local structure for point cloud. Then, a multiscale receptive fields graph attention network (named after MRFGAT) by means of semantic features of local patch for point cloud is proposed in this paper, and the learned feature map for our network can well capture the abundant features information of point cloud. The proposed MRFGAT architecture is tested on ModelNet datasets, and results show it achieves state-of-the-art performance in shape classification tasks, such as it outperforms GAPNet (Chen et al.) model by 0.1% in terms of OA and compete with DGCNN (Wang et al.) model in terms of MA.http://dx.doi.org/10.1155/2021/8832081 |
| spellingShingle | Xi-An Li Li-Yan Wang Jian Lu Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification Complexity |
| title | Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification |
| title_full | Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification |
| title_fullStr | Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification |
| title_full_unstemmed | Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification |
| title_short | Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification |
| title_sort | multiscale receptive fields graph attention network for point cloud classification |
| url | http://dx.doi.org/10.1155/2021/8832081 |
| work_keys_str_mv | AT xianli multiscalereceptivefieldsgraphattentionnetworkforpointcloudclassification AT liyanwang multiscalereceptivefieldsgraphattentionnetworkforpointcloudclassification AT jianlu multiscalereceptivefieldsgraphattentionnetworkforpointcloudclassification |