Open AccessDeepGCNs-Att for Point Cloud Semantic Segmentation
Author(s) -
Xinyu Wang,
Bin Jiang,
Ziheng Zhang,
Cheng Tong,
Qing Me,
Jianguo Xiao,
Yi Tong
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2025/1/012059
Subject(s) - computer science , point cloud , exploit , convolutional neural network , graph , artificial intelligence , segmentation , computation , benchmark (surveying) , deep learning , block (permutation group theory) , theoretical computer science , algorithm , mathematics , geography , combinatorics , cartography , computer security
Compared with traditional CNNs, Graph Convolutional Networks (GCNs), with the graph’s neural network structure, can better characterize non-Euclidean space. Furthermore, with the number of the network layers increasing, deep GCNs demonstrate outstanding performance in mining the partial relationship between the point cloud’s local features. However, the current deep GCNs algorithm cannot sufficiently exploit the point cloud’s global characteristics for semantic segmentation. This paper proposes a novel network structure called DeepGCNs-Att to efficiently aggregate global context features. Moreover, to speed up the computation, we add an Attention layer after the GCN Backbone Block to mutually enhance the connection between the distant points of the non-Euclidean space. Our model is tested on the standard benchmark S3DIS. By comparing with other deep GCNs algorithms, our DeepGCNs-Att’s mIoU has at least two per cent higher than that of other models and even shows excellent results in space complexity and computational complexity under the same number of GCN layers.