# Distance to Center of Mass Encoding for Instance Segmentation

Source: [Distance to Center of Mass Encoding for Instance Segmentation](<https://www.sota2.com/research/paper/68fa63d01e209131cea00dff>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:34.679Z

Authors: Thomio Watanabe, Denis Wolf

Published: 2017-11-24T17:53:15.000Z

## Abstract

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).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1711.09060>)

[PDF](<https://arxiv.org/pdf/1711.09060.pdf>)