Accelerating convolutional neural network models based on wavelet transform

Zihan Shen; Jianchuang Qu; Kaige Wang; Can Wu; Qing Li

doi:10.1117/12.3024724

3 April 2024 Accelerating convolutional neural network models based on wavelet transform

Zihan Shen, Jianchuang Qu, Kaige Wang, Can Wu, Qing Li

Author Affiliations +

Proceedings Volume 13078, Second International Conference on Informatics, Networking, and Computing (ICINC 2023); 130780P (2024) https://doi.org/10.1117/12.3024724
Event: Second International Conference on Informatics, Networking, and Computing (ICINC 2023), 2023, Wuhan, China

Abstract

Convolutional neural networks require a large amount of computing resources and time to achieve progress and development in computer vision tasks. Wavelet transform can provide multi-resolution features of images. By using wavelet transform to preprocess the images in the training set, the main information of the images can be preserved. The processed images can then be used as input for the neural network, significantly reducing the training time. By comparing different wavelet bases and orders, it was found that Bior wavelets showed the best acceleration effect, and the training time was significantly reduced. If the complexity of the model is appropriately increased, the training accuracy can be improved while the training time is reduced by 44% compared with the original time.

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

Citation Download Citation

Zihan Shen, Jianchuang Qu, Kaige Wang, Can Wu, and Qing Li "Accelerating convolutional neural network models based on wavelet transform", Proc. SPIE 13078, Second International Conference on Informatics, Networking, and Computing (ICINC 2023), 130780P (3 April 2024); https://doi.org/10.1117/12.3024724

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