End-to-End Learned Random Walker for Seeded Image Segmentation

TL;DR

This paper introduces an end-to-end neural network approach for seeded image segmentation that learns to predict graph edge weights, improving segmentation accuracy on neuron datasets.

Contribution

It presents a novel learned Random Walker algorithm with optimized edge weights via deep learning, outperforming previous methods on neuron segmentation benchmarks.

Findings

Achieves state-of-the-art results on CREMI neuron segmentation challenge.

Introduces a differentiable framework for learning graph diffusivities.

Simplified gradient sampling maintains competitive performance.

Abstract

We present an end-to-end learned algorithm for seeded segmentation. Our method is based on the Random Walker algorithm, where we predict the edge weights of the underlying graph using a convolutional neural network. This can be interpreted as learning context-dependent diffusivities for a linear diffusion process. Besides calculating the exact gradient for optimizing these diffusivities, we also propose simplifications that sparsely sample the gradient and still yield competitive results. The proposed method achieves the currently best results on a seeded version of the CREMI neuron segmentation challenge.