English

Learned Watershed: End-to-End Learning of Seeded Segmentation

Computer Vision and Pattern Recognition 2017-09-05 v2

Abstract

Learned boundary maps are known to outperform hand- crafted ones as a basis for the watershed algorithm. We show, for the first time, how to train watershed computation jointly with boundary map prediction. The estimator for the merging priorities is cast as a neural network that is con- volutional (over space) and recurrent (over iterations). The latter allows learning of complex shape priors. The method gives the best known seeded segmentation results on the CREMI segmentation challenge.

Keywords

Cite

@article{arxiv.1704.02249,
  title  = {Learned Watershed: End-to-End Learning of Seeded Segmentation},
  author = {Steffen Wolf and Lukas Schott and Ullrich Köthe and Fred Hamprecht},
  journal= {arXiv preprint arXiv:1704.02249},
  year   = {2017}
}

Comments

The first two authors contributed equally

R2 v1 2026-06-22T19:10:56.537Z