Image segmentation via Cellular Automata

Abstract

In this paper, we propose a new approach for building cellular automata to solve real-world segmentation problems. We design and train a cellular automaton that can successfully segment high-resolution images. We consider a colony that densely inhabits the pixel grid, and all cells are governed by a randomized update that uses the current state, the color, and the state of the $3\times 3$ neighborhood. The space of possible rules is defined by a small neural network. The update rule is applied repeatedly in parallel to a large random subset of cells and after convergence is used to produce segmentation masks that are then back-propagated to learn the optimal update rules using standard gradient descent methods. We demonstrate that such models can be learned efficiently with only limited trajectory length and that they show remarkable ability to organize the information to produce a globally consistent segmentation result, using only local information exchange. From a practical perspective, our approach allows us to build very efficient models -- our smallest automaton uses less than 10,000 parameters to solve complex segmentation tasks.

References in corpus (8)

• Deep Residual Learning for Image Recognition
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Conditional Random Fields as Recurrent Neural Networks
• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
• Aggregated Residual Transformations for Deep Neural Networks
• Cellular automata as convolutional neural networks
• Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
• Improving the Neural GPU Architecture for Algorithm Learning

Cited by in corpus (2)

• Collective Intelligence for Deep Learning: A Survey of Recent Developments
• Generative Adversarial Neural Cellular Automata