# Instance Segmentation by Deep Coloring

arXiv: https://arxiv.org/abs/1807.10007 · HTML: https://mlsanity.com/paper/1807.10007/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2018.

## Built on by (most cited first, 3 of 3)

- [How Shift Equivariance Impacts Metric Learning for Instance Segmentation](https://mlsanity.com/paper/2101.05846/) (2021)
- [Self-Supervised Leaf Segmentation under Complex Lighting Conditions](https://mlsanity.com/paper/2203.15943/) (2022)
- [Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring](https://mlsanity.com/paper/2602.05420/) (2026)

## Abstract (arXiv)

We propose a new and, arguably, a very simple reduction of instance segmentation to semantic segmentation. This reduction allows to train feed-forward non-recurrent deep instance segmentation systems in an end-to-end fashion using architectures that have been proposed for semantic segmentation. Our approach proceeds by introducing a fixed number of labels (colors) and then dynamically assigning object instances to those labels during training (coloring). A standard semantic segmentation objective is then used to train a network that can color previously unseen images. At test time, individual object instances can be recovered from the output of the trained convolutional network using simple connected component analysis. In the experimental validation, the coloring approach is shown to be capable of solving diverse instance segmentation tasks arising in autonomous driving (the Cityscapes benchmark), plant phenotyping (the CVPPP leaf segmentation challenge), and high-throughput microscopy image analysis. The source code is publicly available: https://github.com/kulikovv/DeepColoring.