A GNN Architecture With Local and Global-Attention Feature for Image Classification

A GNN Architecture With Local and Global-Attention Feature for Image Classification

Convolutional neural network (CNN) is quite popular in computer vision, especially in image classification with excellent performance. However, limited by the convolution kernels, CNN-based classifiers are hard to extract global feature from the original image, while exact object locations in the en...

Full description

Bibliographic Details
Main Authors: Zhengshun Fei, Junhao Guo, Haibo Gong, Lubin Ye, Eric Attahi, Bingqiang Huang
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Global-attention feature
self-attention
graph global pooling
graph convolutional neural network
convolutional neural network
image processing
Online Access:https://ieeexplore.ieee.org/document/10148955/

Internet

https://ieeexplore.ieee.org/document/10148955/

Similar Items