A Comparison on Instance Segmentation Models

Abstract

Object detection is an important process in computer vision projects/tasks. It is a technique which tries to predict the location of an object by drawing a bounding box around it. This however does not give us any idea about the actual shape of the object. For this we must employ the next stage of computer vision task which is known as Instance Segmentation. This task can be used to find the shape of an object along with its bounding box. In this survey paper, we discuss some of the models that can achieve the task of instance segmentation and a dataset has been discussed. The goal of the paper is to give the reader an idea about the field of instance segmentation.