airo 23(1):

Research Article

Review of Image Classification Algorithms Based on Graph Convolutional Networks

Download435 downloads
  • @ARTICLE{10.4108/airo.3462,
        author={Wenhao Tang},
        title={Review of Image Classification Algorithms Based on Graph Convolutional Networks},
        journal={EAI Endorsed Transactions on AI and Robotics},
        volume={2},
        number={1},
        publisher={EAI},
        journal_a={AIRO},
        year={2023},
        month={7},
        keywords={Graph Convolutional Networks, Convolutional Neural Networks, Graph Neural Networks, Over-smoothing},
        doi={10.4108/airo.3462}
    }
    
  • Wenhao Tang
    Year: 2023
    Review of Image Classification Algorithms Based on Graph Convolutional Networks
    AIRO
    EAI
    DOI: 10.4108/airo.3462
Wenhao Tang1,*
  • 1: Henan Polytechnic University
*Contact email: wenhaotang@home.hpu.edu.cn

Abstract

In recent years, graph convolutional networks (GCNs) have gained widespread attention and applications in image classification tasks. While traditional convolutional neural networks (CNNs) usually represent images as a two-dimensional grid of pixels when processing image data, the classical model of graph neural networks (GNNs), GCNs, can effectively handle data with graph structure, such as social networks, recommender systems, and molecular structures. In this paper, we will introduce the problems that graph convolutional networks have had, such as over-smoothing, and the methods to solve them, and suggest some possible future directions.