# Instance Segmentation as Image Segmentation Annotation

## TL;DR

This paper presents a novel approach to instance segmentation by repurposing the encoder of a segmentation network to classify objects, simplifying the process and reducing computational costs.

## Contribution

It introduces a method that uses the DCME technique with a single segmentation network, avoiding multi-task decoders and improving efficiency.

## Key findings

- Reduces computational cost compared to multi-task networks
- Uses a single segmentation network with encoder-based classification
- Employs the DCME technique for instance segmentation

## Abstract

The instance segmentation problem intends to precisely detect and delineate objects in images. Most of the current solutions rely on deep convolutional neural networks but despite this fact proposed solutions are very diverse. Some solutions approach the problem as a network problem, where they use several networks or specialize a single network to solve several tasks. A different approach tries to solve the problem as an annotation problem, where the instance information is encoded in a mathematical representation. This work proposes a solution based in the DCME technique to solve the instance segmentation with a single segmentation network. Different from others, the segmentation network decoder is not specialized in a multi-task network. Instead, the network encoder is repurposed to classify image objects, reducing the computational cost of the solution.