Performance comparison and optimization of deep learning models based on transfer learning

Rong Liu; Taihao Zhang; Feng Tian; Jing Yang; Hao Yue; Yabian Liu

doi:10.1117/12.3032878

5 July 2024 Performance comparison and optimization of deep learning models based on transfer learning

Rong Liu, Taihao Zhang, Feng Tian, Jing Yang, Hao Yue, Yabian Liu

Author Affiliations +

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 131846O (2024) https://doi.org/10.1117/12.3032878
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

With the continuous development of deep learning technology, the demand for applications in various fields is also increasing, but it also faces the challenges of long training cycles and high model complexity. Therefore, it is critical to compare the performance of different deep learning models to find the solution model best suited to a particular task. This study compares the performance of different deep learning models trained on the same dataset to assist researchers in selecting the most suitable model for a specific task. Additionally, it explores various network structures of mainstream models and fine-tunes them on the test set to evaluate their performance. The results demonstrate that the resnet34 network structure performs the best on the test set. Furthermore, the application of transfer learning to the resnet34 model yielded an accuracy of 95.23% on the test set, providing further validation of transfer learning's effectiveness in model optimization. Therefore, this study offers valuable insights for the selection and optimization of deep learning models.

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

Citation Download Citation

Rong Liu, Taihao Zhang, Feng Tian, Jing Yang, Hao Yue, and Yabian Liu "Performance comparison and optimization of deep learning models based on transfer learning", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 131846O (5 July 2024); https://doi.org/10.1117/12.3032878

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Performance modeling

Data modeling

Deep learning

Education and training

Image classification

Mathematical optimization

Object detection

Show All Keywords

Keywords/Phrases

Search In:

Publication Years