Conference Proceedings

HexCNN: A Framework for Native Hexagonal Convolutional Neural Networks

Yunxiang Zhao, Qiuhong Ke, Flip Korn, Jianzhong Qi, Rui Zhang, C Plant (ed.), H Wang (ed.), A Cuzzocrea (ed.), C Zaniolo (ed.), X Wu (ed.)

20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2020) | IEEE COMPUTER SOC | Published : 2020

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 rectan..

View full abstract