A discrete dual convolution operation

Chuanhui Shan

doi:10.1117/12.3026444

27 March 2024 A discrete dual convolution operation

Chuanhui Shan

Proceedings Volume 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023); 131054G (2024) https://doi.org/10.1117/12.3026444
Event: 3rd International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 2023, Qingdao, China

Abstract

An indispensable contribution to the discovery and advancement of deep learning has been made by convolution neural networks (CNNs) based on discrete convolution operation. In the paper, a new operation, called discrete dual convolution operation, is proposed by imitating discrete convolution operation. The definition, properties and theorems of one-dimensional (1D) and two-dimensional (2D) discrete dual convolution operation are introduced in detail, which aims to encourage the advancement of deep learning and provide a theoretical foundation for the dual convolution neural network's (DCNN’s) presentation.

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

Citation Download Citation

Chuanhui Shan "A discrete dual convolution operation", Proc. SPIE 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 131054G (27 March 2024); https://doi.org/10.1117/12.3026444

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