Image segmentation with traveling waves in an exactly solvable recurrent neural network
This provides a mathematically interpretable method for image segmentation, though it appears incremental in applying exact solutions to recurrent networks.
The paper tackled image segmentation by using spatiotemporal dynamics in a recurrent neural network with complex-valued units, achieving object segmentation across diverse inputs with a single fixed-weight network.
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.