Go wider: an efficient neural network for point cloud analysis via group convolutions
dc.contributor.author | Chen, Can | |
dc.contributor.author | Fragonara, Luca Zanotti | |
dc.contributor.author | Tsourdos, Antonios | |
dc.date.accessioned | 2020-08-12T16:46:37Z | |
dc.date.available | 2020-08-12T16:46:37Z | |
dc.date.issued | 2020-04-01 | |
dc.description.abstract | In order to achieve a better performance for point cloud analysis, many researchers apply deep neural networks using stacked Multi-Layer-Perceptron (MLP) convolutions over an irregular point cloud. However, applying these dense MLP convolutions over a large amount of points (e.g., autonomous driving application) leads to limitations due to the computation and memory capabilities. To achieve higher performances but decrease the computational complexity, we propose a deep-wide neural network, named ShufflePointNet, which can exploit fine-grained local features, but also reduce redundancies using group convolution and channel shuffle operation. Unlike conventional operations that directly apply MLPs on the high-dimensional features of a point cloud, our model goes “wider” by splitting features into groups with smaller depth in advance, having the respective MLP computations applied only to a single group, which can significantly reduce complexity and computation. At the same time, we allow communication between groups by shuffling the feature channel to capture fine-grained features. We further discuss the multi-branch method for wider neural networks being also beneficial to feature extraction for point clouds. We present extensive experiments for shape classification tasks on a ModelNet40 dataset and semantic segmentation task on large scale datasets ShapeNet part, S3DIS and KITTI. Finally, we carry out an ablation study and compare our model to other state-of-the-art algorithms to show its efficiency in terms of complexity and accuracy | en_UK |
dc.identifier.citation | Chen C, Zanotti Fragonara L and Tsourdos A. (2020) Go wider: an efficient neural network for point cloud analysis via group convolutions. Applied Sciences, Volume 10, Issue 7, 2020, Article number 2391 | en_UK |
dc.identifier.issn | 2076-3417 | |
dc.identifier.uri | https://doi.org/10.3390/app10072391 | |
dc.identifier.uri | https://dspace.lib.cranfield.ac.uk/handle/1826/15678 | |
dc.language.iso | en | en_UK |
dc.publisher | MDPI | en_UK |
dc.rights | Attribution 4.0 International | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | * |
dc.subject | neural network | en_UK |
dc.subject | feature shuffle | en_UK |
dc.subject | shape classification | en_UK |
dc.subject | semantic segmentation | en_UK |
dc.subject | point cloud | en_UK |
dc.title | Go wider: an efficient neural network for point cloud analysis via group convolutions | en_UK |
dc.type | Article | en_UK |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Go_Wider_an_efficient_neural_network-2020.pdf
- Size:
- 697.32 KB
- Format:
- Adobe Portable Document Format
- Description:
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.63 KB
- Format:
- Item-specific license agreed upon to submission
- Description: