{
  "id": "1704.02249",
  "version": "v1",
  "published": "2017-04-07T14:40:15.000Z",
  "updated": "2017-04-07T14:40:15.000Z",
  "title": "Learned Watershed: End-to-End Learning of Seeded Segmentation",
  "authors": [
    "Steffen Wolf",
    "Lukas Schott",
    "Ullrich Köthe",
    "Fred Hamprecht"
  ],
  "comment": "The first two authors contributed equally",
  "categories": [
    "cs.CV"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-04-07T14:40:15.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "end-to-end learning",
      "boundary map prediction",
      "complex shape priors",
      "cremi segmentation challenge",
      "learned boundary maps"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}