# Deep Watershed Transform for Instance Segmentation

arXiv: https://arxiv.org/abs/1611.08303 · HTML: https://mlsanity.com/paper/1611.08303/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2016.

## Built on by (most cited first, 30 of 78)

- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [K-Net: Towards Unified Image Segmentation](https://mlsanity.com/paper/2106.14855/) (2021)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [Hierarchical Aggregation for 3D Instance Segmentation](https://mlsanity.com/paper/2108.02350/) (2021)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2104.06404/) (2021)
- [CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation](https://mlsanity.com/paper/2206.08948/) (2022)
- [DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision](https://mlsanity.com/paper/2105.06464/) (2021)
- [Understanding metric-related pitfalls in image analysis validation](https://mlsanity.com/paper/2302.01790/) (2023)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Incremental Few-Shot Instance Segmentation](https://mlsanity.com/paper/2105.05312/) (2021)
- [Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation](https://mlsanity.com/paper/2104.05239/) (2021)
- [LaneAF: Robust Multi-Lane Detection with Affinity Fields](https://mlsanity.com/paper/2103.12040/) (2021)
- [CLUSTSEG: Clustering for Universal Segmentation](https://mlsanity.com/paper/2305.02187/) (2023)
- [OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers](https://mlsanity.com/paper/2207.02255/) (2022)
- [Instance and Panoptic Segmentation Using Conditional Convolutions](https://mlsanity.com/paper/2102.03026/) (2021)
- [TA-Net: Topology-Aware Network for Gland Segmentation](https://mlsanity.com/paper/2110.14593/) (2021)
- [Learning Equivariant Segmentation with Instance-Unique Querying](https://mlsanity.com/paper/2210.00911/) (2022)
- [Unknown Object Segmentation from Stereo Images](https://mlsanity.com/paper/2103.06796/) (2021)
- [A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation](https://mlsanity.com/paper/2105.03186/) (2021)
- [Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2206.10711/) (2022)
- [3D Instance Segmentation of MVS Buildings](https://mlsanity.com/paper/2112.09902/) (2021)
- [kMaX-DeepLab: k-means Mask Transformer](https://mlsanity.com/paper/2207.04044/) (2022)
- [Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings](https://mlsanity.com/paper/2103.14572/) (2021)
- [VideoClick: Video Object Segmentation with a Single Click](https://mlsanity.com/paper/2101.06545/) (2021)
- [Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room](https://mlsanity.com/paper/2108.11801/) (2021)
- [Segmentation in large-scale cellular electron microscopy with deep learning: A literature survey](https://mlsanity.com/paper/2206.07171/) (2022)
- [Beyond mAP: Towards better evaluation of instance segmentation](https://mlsanity.com/paper/2207.01614/) (2022)

## Abstract (arXiv)

Most contemporary approaches to instance segmentation use complex pipelines involving conditional random fields, recurrent neural networks, object proposals, or template matching schemes. In our paper, we present a simple yet powerful end-to-end convolutional neural network to tackle this task. Our approach combines intuitions from the classical watershed transform and modern deep learning to produce an energy map of the image where object instances are unambiguously represented as basins in the energy map. We then perform a cut at a single energy level to directly yield connected components corresponding to object instances. Our model more than doubles the performance of the state-of-the-art on the challenging Cityscapes Instance Level Segmentation task.