Image segmentation with traveling waves in an exactly solvable recurrent neural network

TL;DR

This paper presents an exactly solvable recurrent neural network model that uses spatiotemporal dynamics to perform image segmentation, providing a mathematical understanding of the process and demonstrating its effectiveness across various image types.

Contribution

The paper introduces a novel recurrent neural network with an exact solution that explains its segmentation mechanism and generalizes to different image complexities.

Findings

Effective segmentation of geometric and natural images

Single fixed-weight network achieves diverse segmentation tasks

Mathematical analysis clarifies the network's dynamic mechanism

Abstract

We study image segmentation using spatiotemporal dynamics in a recurrent neural network where the state of each unit is given by a complex number. We show that this network generates sophisticated spatiotemporal dynamics that can effectively divide an image into groups according to a scene's structural characteristics. Using an exact solution of the recurrent network's dynamics, we present a precise description of the mechanism underlying object segmentation in this network, providing a clear mathematical interpretation of how the network performs this task. We then demonstrate a simple algorithm for object segmentation that generalizes across inputs ranging from simple geometric objects in grayscale images to natural images. Object segmentation across all images is accomplished with one recurrent neural network that has a single, fixed set of weights. This demonstrates the expressive potential of recurrent neural networks when constructed using a mathematical approach that brings together their structure, dynamics, and computation.