Accelerating Image Classification with Graph Convolutional Neural Networks using Voronoi Diagrams

TL;DR

This paper presents a novel graph-based image classification framework using Voronoi diagrams and GCNs, achieving faster processing and higher accuracy on complex datasets, and introduces the NVGCN model.

Contribution

It introduces a new Voronoi diagram-based GCN framework and the NVGCN model, enhancing speed and accuracy in image classification tasks.

Findings

Significant improvement in classification accuracy on benchmark datasets.

Reduced pre-processing time compared to traditional CNNs.

Outperformed existing models in complex scene classification.

Abstract

Recent advances in image classification have been significantly propelled by the integration of Graph Convolutional Networks (GCNs), offering a novel paradigm for handling complex data structures. This study introduces an innovative framework that employs GCNs in conjunction with Voronoi diagrams to peform image classification, leveraging their exceptional capability to model relational data. Unlike conventional convolutional neural networks, our approach utilizes a graph-based representation of images, where pixels or regions are treated as vertices of a graph, which are then simplified in the form of the corresponding Delaunay triangulations. Our model yields significant improvement in pre-processing time and classification accuracy on several benchmark datasets, surpassing existing state-of-the-art models, especially in scenarios that involve complex scenes and fine-grained categories. The experimental results, validated via cross-validation, underscore the potential of integrating GCNs with Voronoi diagrams in advancing image classification tasks. This research contributes to the field by introducing a novel approach to image classification, while opening new avenues for developing graph-based learning paradigms in other domains of computer vision and non-structured data. In particular, we have proposed a new version of the GCN in this paper, namely normalized Voronoi Graph Convolution Network (NVGCN), which is faster than the regular GCN.