A Graph Neural Network for superpixel image classification. Issue 1 (April 2021)

• Record Type: Journal Article
• Authors: Long, Jianwu; yan, Zeran; chen, Hongfa
• Is Part Of: Journal of physics. Volume 1871:Issue 1(2021)
• Publication Date: 2021-04
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1871/1/012071
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: The classification of superpixel images by graph neural networks has gradually become a research hotspot. It is a crucial issue to embed super-pixel images from lowdimensional to high-dimensional so as to turn complex image information into graph signals. This paper proposes a method for image classification using a graph neural network (GNN) model. We convert the input image into a region adjacency graph (RAG) composed of superpixels as nodes, and use residual and concat structure to extract deep features. Finally, the loss function that increases the distance between classes and compactness within classes is used as supervision. Experiments have been tested with different numbers of superpixels on multiple datasets, and the results show that our method has a great performance in superpixel images classification.