Image classification based on self-attention convolutional neural network

Xiaohong Cai; Ming Li; Hui Cao; Jingang Ma; Xiaoyan Wang; Xuqiang Zhuang

doi:10.1117/12.2604788

6 August 2021 Image classification based on self-attention convolutional neural network

Xiaohong Cai, Ming Li, Hui Cao, Jingang Ma, Xiaoyan Wang, Xuqiang Zhuang

Proceedings Volume 11913, Sixth International Workshop on Pattern Recognition; 1191307 (2021) https://doi.org/10.1117/12.2604788
Event: Sixth International Workshop on Pattern Recognition, 2021, Chengdu, China

Abstract

Image classification technology is the most basic and important technical branch of computer vision. How to effectively extract effective information from images has become more and more urgent. First, we use the self-attention module to use the correlation between the features to weight and sum the features to get the image category. The self-attention mechanism is simpler to calculate, which greatly reduces the complexity of the model. Secondly, we have also made an optimization strategy for the complex CNN (Convolutional Neural Network) model. This article uses the global average pooling method to replace the fully connected method, which reduces the complexity of the model and generates fewer features. Finally, we verified the feasibility and effectiveness of our model on two data sets.

Citation Download Citation

Xiaohong Cai, Ming Li, Hui Cao, Jingang Ma, Xiaoyan Wang, and Xuqiang Zhuang "Image classification based on self-attention convolutional neural network", Proc. SPIE 11913, Sixth International Workshop on Pattern Recognition, 1191307 (6 August 2021); https://doi.org/10.1117/12.2604788

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available