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

Steffen Wolf; Lukas Schott; Ullrich Kothe; Fred Hamprecht

ICCV 2017poster55 citations

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

Steffen Wolf, Lukas Schott, Ullrich Kothe, Fred Hamprecht

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 convolutional (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.

BibTeX

@inproceedings{iccv2017_learnedwatershed,
  title = {Learned Watershed: End-To-End Learning of Seeded Segmentation},
  author = {Steffen Wolf and Lukas Schott and Ullrich Kothe and Fred Hamprecht},
  booktitle = {ICCV 2017},
  year = {2017}
}