Connections Between Operator-Splitting Methods and Deep Neural Networks with Applications in Image Segmentation

Connections Between Operator-Splitting Methods and Deep Neural Networks with Applications in Image Segmentation

Year:    2023

Author:    Hao Liu, Xue-Cheng Tai, Raymond Chan

Annals of Applied Mathematics, Vol. 39 (2023), Iss. 4 : pp. 406–428

Abstract

Deep neural network is a powerful tool for many tasks. Understanding why it is so successful and providing a mathematical explanation is an important problem and has been one popular research direction in past years. In the literature of mathematical analysis of deep neural networks, a lot of works is dedicated to establishing representation theories. How to make connections between deep neural networks and mathematical algorithms is still under development. In this paper, we give an algorithmic explanation for deep neural networks, especially in their connections with operator splitting. We show that with certain splitting strategies, operator-splitting methods have the same structure as networks. Utilizing this connection and the Potts model for image segmentation, two networks inspired by operator-splitting methods are proposed. The two networks are essentially two operator-splitting algorithms solving the Potts model. Numerical experiments are presented to demonstrate the effectiveness of the proposed networks.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/aam.OA-2023-0027

Annals of Applied Mathematics, Vol. 39 (2023), Iss. 4 : pp. 406–428

Published online:    2023-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    23

Keywords:    Potts model operator splitting deep neural network image segmentation.

Author Details

Hao Liu

Xue-Cheng Tai

Raymond Chan