Recent progress in semantic image segmentation

Abstract

Semantic image segmentation, which becomes one of the key applications in image processing and computer vision domain, has been used in multiple domains such as medical area and intelligent transportation. Lots of benchmark datasets are released for researchers to verify their algorithms. Semantic segmentation has been studied for many years. Since the emergence of Deep Neural Network (DNN), segmentation has made a tremendous progress. In this paper, we divide semantic image segmentation methods into two categories: traditional and recent DNN method. Firstly, we briefly summarize the traditional method as well as datasets released for segmentation, then we comprehensively investigate recent methods based on DNN which are described in the eight aspects: fully convolutional network, upsample ways, FCN joint with CRF methods, dilated convolution approaches, progresses in backbone network, pyramid methods, Multi-level feature and multi-stage method, supervised, weakly-supervised and unsupervised methods. Finally, a conclusion in this area is drawn.

arXiv commentPubulished at Artificial Intelligence review

References in corpus (1)

• Faster and better: a machine learning approach to corner detection

Cited by in corpus (14)

• A Survey of the Recent Architectures of Deep Convolutional Neural Networks
• A survey of the Vision Transformers and their CNN-Transformer based Variants
• Modality specific U-Net variants for biomedical image segmentation: A survey
• Hybrid quantum convolutional neural networks model for COVID-19 prediction using chest X-Ray images
• MudrockNet: Semantic Segmentation of Mudrock SEM Images through Deep Learning
• G-image Segmentation: Similarity-preserving Fuzzy C-Means with Spatial Information Constraint in Wavelet Space
• FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anything
• Image and Model Transformation with Secret Key for Vision Transformer
• Concurrent Segmentation and Object Detection CNNs for Aircraft Detection and Identification in Satellite Images
• Low-latency Perception in Off-Road Dynamical Low Visibility Environments
• Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance
• Dynamic Spectral Residual Superpixels
• MEAL: Manifold Embedding-based Active Learning
• Feature boosting with efficient attention for scene parsing