A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images

Abstract

Semantic segmentation is the pixel-wise labelling of an image. Since the problem is defined at the pixel level, determining image class labels only is not acceptable, but localising them at the original image pixel resolution is necessary. Boosted by the extraordinary ability of convolutional neural networks (CNN) in creating semantic, high level and hierarchical image features; several deep learning-based 2D semantic segmentation approaches have been proposed within the last decade. In this survey, we mainly focus on the recent scientific developments in semantic segmentation, specifically on deep learning-based methods using 2D images. We started with an analysis of the public image sets and leaderboards for 2D semantic segmentation, with an overview of the techniques employed in performance evaluation. In examining the evolution of the field, we chronologically categorised the approaches into three main periods, namely pre-and early deep learning era, the fully convolutional era, and the post-FCN era. We technically analysed the solutions put forward in terms of solving the fundamental problems of the field, such as fine-grained localisation and scale invariance. Before drawing our conclusions, we present a table of methods from all mentioned eras, with a summary of each approach that explains their contribution to the field. We conclude the survey by discussing the current challenges of the field and to what extent they have been solved.

published in the J. of Applied Artificial Intelligence (09 Feb 2022)

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Fully Convolutional Networks for Semantic Segmentation
• A survey of loss functions for semantic segmentation
• SOLOv2: Dynamic and Fast Instance Segmentation
• ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images
• Rethinking Pre-training and Self-training
• Contrastive learning of global and local features for medical image segmentation with limited annotations
• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains
• Stacked Deconvolutional Network for Semantic Segmentation
• Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
• DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation

Cited by in corpus (8)

• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• IDDA: a large-scale multi-domain dataset for autonomous driving
• DS6, Deformation-aware Semi-supervised Learning: Application to Small Vessel Segmentation with Noisy Training Data
• A Spacecraft Dataset for Detection, Segmentation and Parts Recognition
• Deep Learning for Robust Motion Segmentation with Non-Static Cameras
• TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
• TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos
• Minimizing Labeling Effort for Tree Skeleton Segmentation using an Automated Iterative Training Methodology