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

Lorenzo Cerrone, Alexander Zeilmann, Fred A. Hamprecht; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 12559-12568

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 un- derlying graph using a convolutional neural network. This can be interpreted as learning context-dependent diffusiv- ities for a linear diffusion process. After calculating the exact gradient for optimizing these diffusivities, we pro- pose simplifications that sparsely sample the gradient while still maintaining competitive results. The proposed method achieves the currently best results on the seeded CREMI neuron segmentation challenge.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Cerrone_2019_CVPR,
author = {Cerrone, Lorenzo and Zeilmann, Alexander and Hamprecht, Fred A.},
title = {End-To-End Learned Random Walker for Seeded Image Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}