# MaskPlus: Improving Mask Generation for Instance Segmentation

## TL;DR

MaskPlus introduces five novel optimization techniques to enhance mask generation in instance segmentation, addressing conflicts with detection components and improving overall accuracy on the COCO dataset.

## Contribution

The paper proposes five independent optimization techniques that improve mask generation in Mask R-CNN, reducing conflicts and increasing accuracy in instance segmentation.

## Key findings

- Significant accuracy improvements on COCO dataset
- Effective reduction of conflicts between mask and detection branches
- Flexible techniques applicable to various architectures

## Abstract

Instance segmentation is a promising yet challenging topic in computer vision. Recent approaches such as Mask R-CNN typically divide this problem into two parts -- a detection component and a mask generation branch, and mostly focus on the improvement of the detection part. In this paper, we present an approach that extends Mask R-CNN with five novel optimization techniques for improving the mask generation branch and reducing the conflicts between the mask branch and the detection component in training. These five techniques are independent to each other and can be flexibly utilized in building various instance segmentation architectures for increasing the overall accuracy. We demonstrate the effectiveness of our approach with tests on the COCO dataset.