Superpixel Image Classification with Graph Convolutional Neural Networks Based on Learnable Positional Embedding

被引:14
作者
Bae, Ji-Hun [1 ]
Yu, Gwang-Hyun [1 ]
Lee, Ju-Hwan [1 ]
Vu, Dang Thanh [1 ]
Anh, Le Hoang [1 ]
Kim, Hyoung-Gook [2 ]
Kim, Jin-Young [1 ]
机构
[1] Chonnam Natl Univ, Dept ICT Convergence Syst Engn, 77 Yongbong Ro, Gwangju 61186, South Korea
[2] Kwangwoon Univ, Dept Elect Convergence Engn, 20 Gwangun Ro, Seoul 01897, South Korea
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 18期
关键词
graph convolutional neural network (GCNN); superpixel image classification; learnable positional embedding;
D O I
10.3390/app12189176
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Graph convolutional neural networks (GCNNs) have been successfully applied to a wide range of problems, including low-dimensional Euclidean structural domains representing images, videos, and speech and high-dimensional non-Euclidean domains, such as social networks and chemical molecular structures. However, in computer vision, the existing GCNNs are not provided with positional information to distinguish between graphs of new structures; therefore, the performance of the image classification domain represented by arbitrary graphs is significantly poor. In this work, we introduce how to initialize the positional information through a random walk algorithm and continuously learn the additional position-embedded information of various graph structures represented over the superpixel images we choose for efficiency. We call this method the graph convolutional network with learnable positional embedding applied on images (IMGCN-LPE). We apply IMGCN-LPE to three graph convolutional models (the Chebyshev graph convolutional network, graph convolutional network, and graph attention network) to validate performance on various benchmark image datasets. As a result, although not as impressive as convolutional neural networks, the proposed method outperforms various other conventional convolutional methods and demonstrates its effectiveness among the same tasks in the field of GCNNs.
引用
收藏
页数:14
相关论文
共 48 条
[41]  
Wu L, 2021, ARXIV
[42]  
Xiao, 2017, ARXIV
[43]   A Low-power Pyramid Motion Estimation Engine for 4K@30fps Realtime HEVC Video Encoding [J].
Xu, Ke ;
Huang, Bo ;
Liu, Xiangkai ;
Tu, Xueying ;
Wu, Zhuoyan ;
Yan, Zhanpeng ;
Liu, Peng ;
Han, Bin ;
Li, Yu .
2018 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2018,
[44]   Saliency Detection via Graph-Based Manifold Ranking [J].
Yang, Chuan ;
Zhang, Lihe ;
Lu, Huchuan ;
Ruan, Xiang ;
Yang, Ming-Hsuan .
2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, :3166-3173
[45]  
You JX, 2019, PR MACH LEARN RES, V97
[46]   Pyramid Graph Networks with Connection Attentions for Region-Based One-Shot Semantic Segmentation [J].
Zhang, Chi ;
Lin, Guosheng ;
Liu, Fayao ;
Guo, Jiushuang ;
Wu, Qingyao ;
Yao, Rui .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :9586-9594
[47]   Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection [J].
Zhang, Kaihua ;
Li, Tengpeng ;
Shen, Shiwen ;
Liu, Bo ;
Chen, Jin ;
Liu, Qingshan .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :9047-9056
[48]   Multiple-Aspect Attentional Graph Neural Networks for Online Social Network User Localization [J].
Zhong, Ting ;
Wang, Tianliang ;
Wang, Jiahao ;
Wu, Jin ;
Zhou, Fan .
IEEE ACCESS, 2020, 8 :95223-95234