Go wider: an efficient neural network for point cloud analysis via group convolutions

Simple item page
dc.contributor.authorChen, Can
dc.contributor.authorFragonara, Luca Zanotti
dc.contributor.authorTsourdos, Antonios
dc.date.accessioned2020-08-12T16:46:37Z
dc.date.available2020-08-12T16:46:37Z
dc.date.issued2020-04-01
dc.description.abstractIn 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 accuracyen_UK
dc.identifier.citationChen 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 2391en_UK
dc.identifier.issn2076-3417
dc.identifier.urihttps://doi.org/10.3390/app10072391
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/15678
dc.language.isoenen_UK
dc.publisherMDPIen_UK
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectneural networken_UK
dc.subjectfeature shuffleen_UK
dc.subjectshape classificationen_UK
dc.subjectsemantic segmentationen_UK
dc.subjectpoint clouden_UK
dc.titleGo wider: an efficient neural network for point cloud analysis via group convolutionsen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Go_Wider_an_efficient_neural_network-2020.pdf
Size:
697.32 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)