# Distance to Center of Mass Encoding for Instance Segmentation

arXiv: https://arxiv.org/abs/1711.09060 · HTML: https://mlsanity.com/paper/1711.09060/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2017.

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

- [A Simple and Generalist Approach for Panoptic Segmentation](https://mlsanity.com/paper/2408.16504/) (2024)
- [Transformer Assisted Convolutional Network for Cell Instance Segmentation](https://mlsanity.com/paper/2110.02270/) (2021)
- [Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation](https://mlsanity.com/paper/2609.16874/) (2026)

## Abstract (arXiv)

The instance segmentation can be considered an extension of the object detection problem where bounding boxes are replaced by object contours. Strictly speaking the problem requires to identify each pixel instance and class independently of the artifice used for this mean. The advantage of instance segmentation over the usual object detection lies in the precise delineation of objects improving object localization. Additionally, object contours allow the evaluation of partial occlusion with basic image processing algorithms. This work approaches the instance segmentation problem as an annotation problem and presents a novel technique to encode and decode ground truth annotations. We propose a mathematical representation of instances that any deep semantic segmentation model can learn and generalize. Each individual instance is represented by a center of mass and a field of vectors pointing to it. This encoding technique has been denominated Distance to Center of Mass Encoding (DCME).