Connections between Operator-splitting Methods and Deep Neural Networks with Applications in Image Segmentation
This provides an algorithmic explanation for deep neural networks, potentially aiding in mathematical understanding and applications in image segmentation, though it appears incremental.
The paper connects operator-splitting methods to deep neural networks, proposing two networks based on this connection for image segmentation using the Potts model, with numerical experiments showing effectiveness.
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.