Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey

by   Farhana Sultana, et al.

From the autonomous car driving to medical diagnosis, the requirement of the task of image segmentation is everywhere. Segmentation of an image is one of the indispensable tasks in computer vision. This task is comparatively complicated than other vision tasks as it needs low level spatial information. Basically, image segmentation can be of two types: semantic segmentation and instance segmentation. The combined version of these two basic tasks is known as panoptic segmentation. In the recent era, the success of deep convolutional neural network (CNN) has influenced the field of segmentation greatly and gave us various successful models till date. In this survey, we are going to take a glance on the evolution of both semantic and instance segmentation work based on CNN. We have also specified architectural details of some state-of-the-art models and discuss their comparative training details to present a lucid understanding of hyper-parameter tuning of those models. We have also drawn a comparison among the performance of those models on different datasets.


page 4

page 5

page 13

page 16

page 28


Semantic Segmentation using Vision Transformers: A survey

Semantic segmentation has a broad range of applications in a variety of ...

Instance Segmentation as Image Segmentation Annotation

The instance segmentation problem intends to precisely detect and deline...

Two-Stream UNET Networks for Semantic Segmentation in Medical Images

Recent advances of semantic image segmentation greatly benefit from deep...

Image Segmentation Using Deep Learning: A Survey

Image segmentation is a key topic in image processing and computer visio...

Mask2Former for Video Instance Segmentation

We find Mask2Former also achieves state-of-the-art performance on video ...

PointRend: Image Segmentation as Rendering

We present a new method for efficient high-quality image segmentation of...

Kartezio: Evolutionary Design of Explainable Pipelines for Biomedical Image Analysis

An unresolved issue in contemporary biomedicine is the overwhelming numb...

Please sign up or login with your details

Forgot password? Click here to reset