L-GhostNet: Extract Better Quality Features

L-GhostNet: Extract Better Quality Features

A lightweight image recognition model, L-GhostNet based on improved GhostNet, is proposed to address the problems of extensive computation and high storage cost of deep convolutional neural networks. The model incorporated learning group convolution and improved CA into GhostNet to reduce the calcul...

Full description

Bibliographic Details
Main Authors: Jing Chi, Shaohua Guo, Haopeng Zhang, Yu Shan
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Coordinate attention
ghostNet
group convolution
lightweight convolutional neural network
Online Access:https://ieeexplore.ieee.org/document/10005301/

Internet

https://ieeexplore.ieee.org/document/10005301/

Similar Items