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

arXiv: https://arxiv.org/abs/1704.02249 · HTML: https://mlsanity.com/paper/1704.02249/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2017.

## Built on by (most cited first, 5 of 5)

- [Cell Instance Segmentation: The Devil Is in the Boundaries](https://mlsanity.com/paper/2510.09848/) (2025)
- [Triplet-Watershed for Hyperspectral Image Classification](https://mlsanity.com/paper/2103.09384/) (2021)
- [A Novel Approach to Regularising 1NN classifier for Improved Generalization](https://mlsanity.com/paper/2402.08405/) (2024)
- [BuyTheDips: PathLoss for improved topology-preserving deep learning-based image segmentation](https://mlsanity.com/paper/2207.11446/) (2022)
- [Playing with Kruskal: algorithms for flat and hierarchical watershed cuts](https://mlsanity.com/paper/2610.10012/) (2026)

## Abstract (arXiv)

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.