Adaptive and generic improvements to ResNet Backbone in image classification

Zhengdi Sima; Jingyu Tao; Zhaochen Liu

doi:10.1117/12.3055002

11 December 2024 Adaptive and generic improvements to ResNet Backbone in image classification

Zhengdi Sima, Jingyu Tao, Zhaochen Liu

Author Affiliations +

Proceedings Volume 13445, International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2024); 134453A (2024) https://doi.org/10.1117/12.3055002
Event: International Conference on Electronics. Electrical and Information Engineering (ICEEIE 2024), 2024, Haikou, China

Abstract

Image classification is one of the important basic tasks in computer vision. As the basic module of various complex tasks, ResNet of various types plays an important role as a back- bone for various tasks. This paper aims to use a series of effective methods to improve the performance of traditional ResNet and, to some extent, improve its generalization ability. We improve the methods of ResNet in terms of refined image conversion, optimizer improvement, adaptive learning rate scheduling, difference classification weighting, and experimentally using validation set integration, as well as in the structure of ResNet itself by incorporating residual structures in the network by using ResNet. With these bar improvements, our new baseline performance has made a significant difference, and we also have excellent performance in generalization migration to multiple tasks.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Zhengdi Sima, Jingyu Tao, and Zhaochen Liu "Adaptive and generic improvements to ResNet Backbone in image classification", Proc. SPIE 13445, International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2024), 134453A (11 December 2024); https://doi.org/10.1117/12.3055002

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