| Paper ID | MLSP-4.3 |
| Paper Title |
HIGCNN: HIERARCHICAL INTERLEAVED GROUP CONVOLUTIONAL NEURAL NETWORKS FOR POINT CLOUDS ANALYSIS |
| Authors |
Jisheng Dang, Jun Yang, Lanzhou Jiaotong University, China |
| Session | MLSP-4: Machine Learning for Classification Applications 1 |
| Location | Gather.Town |
| Session Time: | Tuesday, 08 June, 14:00 - 14:45 |
| Presentation Time: | Tuesday, 08 June, 14:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Machine Learning for Signal Processing: [MLR-PRCL] Pattern recognition and classification |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Although previous works for point clouds analysis have achieved remarkable performance, it is difficult for them to achieve a good trade-off between accuracy and complexity. In this paper, we present an efficient and lightweight neural network for point clouds analysis, named HIGCNN, which can achieve better performance but lower complexity compared to existing methods. The key component in our approach is the hierarchical interleaved group convolution (HIGConv) module. We first present a neighborhood attention convolution (NAC) operation to fully mine fine-grained local geometric features inside each local area. With the proposed NAC, we further design a HIGConv to encode both discriminative fine-grained local geometric features and nonlocal point-wise features with fewer parameters and lower computational costs. To further capture fine-grained contextual features, we propose a multi-scale relation (MSR) module to fully explore the relationship among different scale areas. Extensive experiments show that our HIGCNN surpasses state-of-the-art approaches for classification and semantic segmentation on four benchmarks ModelNet40, S3DIS, vKITTI and SemanticKITTI in terms of accuracy and complexity. |
