VisGraphNet: a complex network interpretation of convolutional neural features

TL;DR

This paper introduces VisGraphNet, a novel approach that models neural network feature maps as visibility graphs, providing an alternative perspective for texture image classification and demonstrating competitive performance on benchmark datasets.

Contribution

The work applies visibility graphs to neural network features for the first time, offering a new interpretative framework for texture classification tasks.

Findings

Competitive accuracy on benchmark datasets

Effective in plant species identification from leaf images

Provides a new perspective for neural network feature analysis

Abstract

Here we propose and investigate the use of visibility graphs to model the feature map of a neural network. The model, initially devised for studies on complex networks, is employed here for the classification of texture images. The work is motivated by an alternative viewpoint provided by these graphs over the original data. The performance of the proposed method is verified in the classification of four benchmark databases, namely, KTHTIPS-2b, FMD, UIUC, and UMD and in a practical problem, which is the identification of plant species using scanned images of their leaves. Our method was competitive with other state-of-the-art approaches, confirming the potential of techniques used for data analysis in different contexts to give more meaningful interpretation to the use of neural networks in texture classification.