Hexagonal Convolutional Neural Networks for Hexagonal Grids

Hexagonal grids use a hierarchical subdivision tessellation to cover the entire plane or sphere. Due to the 6-fold rotational symmetry, hexagonal grids have some advantages (e.g. isoperimetry, equidistant neighbors, and uniform connectivity) over quadrangular and triangular girds, which makes them s...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.142738-142749
Main Authors: Luo, Junren, Zhang, Wanpeng, Su, Jiongming, Xiang, Fengtao
Format: Article
Language:English
Subjects:
Apertures
Artificial neural networks
CNN
Convolution
Convolutional neural networks
Data processing
Datasets
Decision making
discrete grids
Hexagon
Image classification
Machine learning
Neural networks
Shape
Tessellation
Three dimensional models
Two dimensional displays
Zinc
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hexagonal grids use a hierarchical subdivision tessellation to cover the entire plane or sphere. Due to the 6-fold rotational symmetry, hexagonal grids have some advantages (e.g. isoperimetry, equidistant neighbors, and uniform connectivity) over quadrangular and triangular girds, which makes them suitable to tackle tasks of geospatial information processing and intelligent decision-making. In this paper, we first introduce some applications based on the hexagonal grids. Then, we introduce the planer and spherical hexagonal grids and analyze the group representations for them, we review geometric deep learning, some Convolutional Neural Networks (CNNs) for hexagonal grids, and group-based equivariant convolution. Next in importance, we propose the HexagonNet for hexagonal grids, and define a new convolution operator and pooling operator. Finally, in order to evaluate the effectiveness of the proposed HexagonNet, we perform experiments on two tasks: aerial scene classification on the aerial image dataset (AID), and 3D shape classification on the ModelNet40 dataset. The experimental results verify the practical applicability of the HexagonNet given some fixed parameter budgets.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2944766