Subgraph Clustering and Atom Learning for Improved Image Classification

TL;DR

This paper introduces the Graph Sub-Graph Network (GSN), a hybrid model combining CNNs and GNNs with clustering and dictionary learning to improve image classification, especially in medical imaging with limited data.

Contribution

The paper presents a novel GSN model that integrates clustering, atom learning, and graph neural networks for enhanced image classification performance.

Findings

GSN outperforms traditional CNNs on benchmark datasets

The model effectively learns class-distinguishable features

Improves accuracy in medical image classification tasks

Abstract

In this study, we present the Graph Sub-Graph Network (GSN), a novel hybrid image classification model merging the strengths of Convolutional Neural Networks (CNNs) for feature extraction and Graph Neural Networks (GNNs) for structural modeling. GSN employs k-means clustering to group graph nodes into clusters, facilitating the creation of subgraphs. These subgraphs are then utilized to learn representative `atoms` for dictionary learning, enabling the identification of sparse, class-distinguishable features. This integrated approach is particularly relevant in domains like medical imaging, where discerning subtle feature differences is crucial for accurate classification. To evaluate the performance of our proposed GSN, we conducted experiments on benchmark datasets, including PascalVOC and HAM10000. Our results demonstrate the efficacy of our model in optimizing dictionary configurations across varied classes, which contributes to its effectiveness in medical classification tasks. This performance enhancement is primarily attributed to the integration of CNNs, GNNs, and graph learning techniques, which collectively improve the handling of datasets with limited labeled examples. Specifically, our experiments show that the model achieves a higher accuracy on benchmark datasets such as Pascal VOC and HAM10000 compared to conventional CNN approaches.