用像素相关性构建新图结构，提升GNN图像分类准确率
Inferring the Graph Structure of Images for Graph Neural Networks
- 基于像素值相关性构造行、列及乘积图，替代传统网格图
- 在MNIST和Fashion-MNIST上，新图结构使分类准确率显著提高
- 适合研究GNN图结构设计或图像表示的学者参考
MNIST等图像数据集是测试图神经网络（GNN）架构的关键基准。传统方法将图像表示为网格图，每个节点对应一个像素，边连接相邻像素（上下左右），图信号为像素强度值。该图常作为图卷积网络（如Graph CNN、GAT、GatedGCN）的输入以实现图像分类。本文通过[5,6]的方法，基于像素值间的相关性，为每幅图像构建行相关图、列相关图及乘积图，探索替代传统网格图与超像素方法的新型图结构。实验表明，将这些新图结构及其特征输入下游GNN模型，能显著优于文献中使用的传统网格图与超像素方法。
原文摘要 · Abstract (English)
Image datasets such as MNIST are a key benchmark for testing Graph Neural Network (GNN) architectures. The images are traditionally represented as a grid graph with each node representing a pixel and edges connecting neighboring pixels (vertically and horizontally). The graph signal is the values (intensities) of each pixel in the image. The graphs are commonly used as input to graph neural networks (e.g., Graph Convolutional Neural Networks (Graph CNNs) [1, 2], Graph Attention Networks (GAT) [3], GatedGCN [4]) to classify the images. In this work, we improve the accuracy of downstream graph neural network tasks by finding alternative graphs to the grid graph and superpixel methods to represent the dataset images, following the approach in [5, 6]. We find row correlation, column correlation, and product graphs for each image in MNIST and Fashion-MNIST using correlations between the pixel values building on the method in [5, 6]. Experiments show that using these different graph representations and features as input into downstream GNN models improves the accuracy over using the traditional grid graph and superpixel methods in the literature.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。