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

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.

arXiv comment38 pages, 29 figures, 8 tables

References in corpus (57)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• SSD: Single Shot MultiBox Detector
• Deep Learning in Neural Networks: An Overview
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Deep Learning using Rectified Linear Units (ReLU)
• MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
• Wide Residual Networks
• ParseNet: Looking Wider to See Better
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• An Introduction to Convolutional Neural Networks
• Fully Convolutional Networks for Semantic Segmentation
• Learning to Segment Object Candidates
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• High-Resolution Representations for Labeling Pixels and Regions
• Learning Deconvolution Network for Semantic Segmentation
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Semantic Segmentation using Adversarial Networks
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• Feature Pyramid Networks for Object Detection
• Advancements in Image Classification using Convolutional Neural Network
• Aggregated Residual Transformations for Deep Neural Networks
• Path Aggregation Network for Instance Segmentation
• Scalable, High-Quality Object Detection
• Pyramid Scene Parsing Network
• A Review of Object Detection Models based on Convolutional Neural Network
• Pyramid Attention Network for Semantic Segmentation
• Simultaneous Detection and Segmentation
• A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
• Bridging Category-level and Instance-level Semantic Image Segmentation
• HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• Single-Shot Refinement Neural Network for Object Detection
• Proposal-free Network for Instance-level Object 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
• Panoptic Feature Pyramid Networks
• Geometric Context from Videos
• Understanding Batch Normalization
• TensorMask: A Foundation for Dense Object Segmentation
• Deep Watershed Transform for Instance Segmentation
• Scalable Object Detection using Deep Neural Networks
• DeepBox: Learning Objectness with Convolutional Networks
• Pedestrian Detection with Unsupervised Multi-Stage Feature Learning
• InstanceCut: from Edges to Instances with MultiCut
• An End-to-End Network for Panoptic Segmentation
• Hypercolumns for Object Segmentation and Fine-grained Localization
• Collaborative Video Object Segmentation by Foreground-Background Integration
• Understanding symmetries in deep networks
• UPSNet: A Unified Panoptic Segmentation Network
• Memory Aggregation Networks for Efficient Interactive Video Object Segmentation

Cited by in corpus (8)

• Vision-based Robotic Grasping From Object Localization, Object Pose Estimation to Grasp Estimation for Parallel Grippers: A Review
• Review: Deep Learning in Electron Microscopy
• MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images
• Artificial Intelligence and Deep Learning Algorithms for Epigenetic Sequence Analysis: A Review for Epigeneticists and AI Experts
• Group channel pruning and spatial attention distilling for object detection
• Multi-modal Scene-compliant User Intention Estimation in Navigation
• ConAM: Confidence Attention Module for Convolutional Neural Networks
• Hoechst Is All You Need: Lymphocyte Classification with Deep Learning