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

2020/01/31 by Farhana Sultana, Abu Sufian, Paramartha Dutta · 342 citations
Computer Science · Mathematics · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Artificial intelligence #Computer science #Computer vision #Convolutional neural network #Deep learning #Field (mathematics) #Image segmentation #Machine learning #Mathematics #Medical Image Segmentation Techniques #Pattern recognition (psychology) #Scale-space segmentation #Segmentation #Segmentation-based object categorization #Task (project management) #cs.CV

paper · pdf · doi:10.1016/j.knosys.2020.106062

published in Knowledge-Based Systems 201-202, 106062 (Elsevier BV) · 38 pages, 29 figures, 8 tables

openalex publication_date 2020/05/26 · arxiv created 2020/05/29 · arxiv updated 2020/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

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 networks (CNN) has influenced the field of segmentation greatly and gave us various successful models to date. In this survey, we are going to take a glance at the evolution of both semantic and instance segmentation work based on CNN. We have also specified comparative architectural details of some state-of-the-art models and discuss their 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. Lastly, we have given a glimpse of some state-of-the-art panoptic segmentation models.

Citations

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Learning to Segment Object Candidates
• Scalable, High-Quality Object Detection
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• The Pascal Visual Object Classes (VOC) Challenge
• Deep Learning in Neural Networks: An Overview
• SIFT Flow: Dense Correspondence across Scenes and Its Applications
• Gradient-based learning applied to document recognition
• ImageNet Large Scale Visual Recognition Challenge
• Backpropagation Applied to Handwritten Zip Code Recognition
• ImageNet classification with deep convolutional neural networks
• Rapid object detection using a boosted cascade of simple features
• SSD: Single Shot MultiBox Detector
• Proposal-free Network for Instance-level Object Segmentation
• An Introduction to Convolutional Neural Networks
• HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
• Wide Residual Networks
• Bridging Category-level and Instance-level Semantic Image Segmentation
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Single-Shot Refinement Neural Network for Object Detection
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Path Aggregation Network for Instance Segmentation
• Pyramid Attention Network for Semantic Segmentation
• Understanding Batch Normalization
• UPSNet: A Unified Panoptic Segmentation Network
• Deep learning
• An End-to-End Network for Panoptic Segmentation
• TensorMask: A Foundation for Dense Object Segmentation
• High-Resolution Representations for Labeling Pixels and Regions
• Scalable Object Detection using Deep Neural Networks
• Feature Pyramid Networks for Object Detection
• InstanceCut: from Edges to Instances with MultiCut
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Pedestrian Detection with Unsupervised Multi-Stage Feature Learning
• Deep Watershed Transform for Instance Segmentation
• DeepBox: Learning Objectness with Convolutional Networks
• Simultaneous Detection and Segmentation
• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
• Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
• Pyramid Scene Parsing Network
• Fully Convolutional Networks for Semantic Segmentation
• Learning Deconvolution Network for Semantic Segmentation
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Hypercolumns for Object Segmentation and Fine-grained Localization
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Aggregated Residual Transformations for Deep Neural Networks
• Panoptic Feature Pyramid Networks
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• Recent advances in convolutional neural networks
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation