HexCNN: A Framework for Native Hexagonal Convolutional Neural Networks

TL;DR

HexCNN introduces a native hexagonal convolutional neural network framework that processes hexagon-shaped inputs directly, significantly improving efficiency and reducing memory and computation overheads compared to existing imitation methods.

Contribution

This paper presents HexCNN, a novel framework for native hexagonal CNNs that avoids the overhead of imitation methods by directly operating on hexagon-shaped inputs and filters.

Findings

HexCNN reduces training time by up to 42.2%.

HexCNN saves memory space by up to 25% and 41.7%.

HexCNN outperforms existing methods in efficiency and resource usage.

Abstract

Hexagonal CNN models have shown superior performance in applications such as IACT data analysis and aerial scene classification due to their better rotation symmetry and reduced anisotropy. In order to realize hexagonal processing, existing studies mainly use the ZeroOut method to imitate hexagonal processing, which causes substantial memory and computation overheads. We address this deficiency with a novel native hexagonal CNN framework named HexCNN. HexCNN takes hexagon-shaped input and performs forward and backward propagation on the original form of the input based on hexagon-shaped filters, hence avoiding computation and memory overheads caused by imitation. For applications with rectangle-shaped input but require hexagonal processing, HexCNN can be applied by padding the input into hexagon-shape as preprocessing. In this case, we show that the time and space efficiency of HexCNN still outperforms existing hexagonal CNN methods substantially. Experimental results show that compared with the state-of-the-art models, which imitate hexagonal processing but using rectangle-shaped filters, HexCNN reduces the training time by up to 42.2%. Meanwhile, HexCNN saves the memory space cost by up to 25% and 41.7% for loading the input and performing convolution, respectively.