# Weakly Supervised Instance Segmentation Using Hybrid Network

## TL;DR

This paper introduces a hybrid network for weakly supervised instance segmentation that effectively handles invalid masks, especially for small objects, leading to significant performance improvements over existing methods.

## Contribution

The proposed hybrid network architecture addresses the challenge of invalid initial masks in weakly supervised segmentation, especially for small objects, improving overall accuracy.

## Key findings

- Significant performance boost on small object segmentation.
- Outperforms all state-of-the-art methods.
- Effective handling of invalid masks in weak supervision.

## Abstract

Weakly-supervised instance segmentation, which could greatly save labor and time cost of pixel mask annotation, has attracted increasing attention in recent years. The commonly used pipeline firstly utilizes conventional image segmentation methods to automatically generate initial masks and then use them to train an off-the-shelf segmentation network in an iterative way. However, the initial generated masks usually contains a notable proportion of invalid masks which are mainly caused by small object instances. Directly using these initial masks to train segmentation model is harmful for the performance. To address this problem, we propose a hybrid network in this paper. In our architecture, there is a principle segmentation network which is used to handle the normal samples with valid generated masks. In addition, a complementary branch is added to handle the small and dim objects without valid masks. Experimental results indicate that our method can achieve significantly performance improvement both on the small object instances and large ones, and outperforms all state-of-the-art methods.