# HexCNN: A Framework for Native Hexagonal Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2101.10897 · HTML: https://mlsanity.com/paper/2101.10897/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 25 Jan 2021.

## Builds on (most cited first, 8 of 8)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [HexagDLy - Processing hexagonally sampled data with CNNs in PyTorch](https://mlsanity.com/paper/1903.01814/) (2019)
- [Neurohex: A Deep Q-learning Hex Agent](https://mlsanity.com/paper/1604.07097/) (2016)
- [CBHE: Corner-based Building Height Estimation for Complex Street Scene Images](https://mlsanity.com/paper/1904.11128/) (2019)
- [Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework](https://mlsanity.com/paper/1911.11251/) (2019)
- [Design of Kernels in Convolutional Neural Networks for Image Classification](https://mlsanity.com/paper/1511.09231/) (2015)
- [Inferring astrophysical X-ray polarization with deep learning](https://mlsanity.com/paper/2005.08126/) (2020)

## Built on by (most cited first, 2 of 2)

- [WGCN: Graph Convolutional Networks with Weighted Structural Features](https://mlsanity.com/paper/2104.14060/) (2021)
- [Biologically inspired deep residual networks for computer vision applications](https://mlsanity.com/paper/2205.02551/) (2022)

## Abstract (arXiv)

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.