Semantic Image Segmentation: Two Decades of Research

DOI10.1561/0600000095MaRDI QIDQ5046690zbMATH OpenOpenAlexFDO

Authors Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii

Publication date 9 November 2022

Published in Foundations and Trends® in Computer Graphics and Vision (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1561/0600000095

zbMATH Keywords

deep learninglearning and statistical methodspattern recognition and learningsegmentation and grouping

Mathematics Subject Classification ID

Computer science (68-XX)

Recommendations

• scientific article; zbMATH DE number 7109071
• A survey of panoptic segmentation methods
• A Comprehensive Review of Modern Object Segmentation Approaches
• Survey on content-based image segmentation methods
• Overview of image segmentation methods

Cites work

• 10.1162/jmlr.2003.3.4-5.993
• A theory of learning from different domains
• Category level object segmentation by combining bag-of-words models with Dirichlet processes and random fields
• Domain-adversarial training of neural networks
• Learning from multiple sources
• Learning to Exploit the Prior Network Knowledge for Weakly Supervised Semantic Segmentation
• Markov random fields in image segmentation
• Prediction, Learning, and Games
• Unsupervised learning by probabilistic latent semantic analysis
• Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach

Cited in

(1)

• scientific article; zbMATH DE number 7109071 (Why is no real title available?)

Describes a project that uses

Uses Software

• DeepLab
• ViT
• Swin Transformer
• RefineNet
• Faster R-CNN
• SIFT
• Panoptic-DeepLab
• DeeperLab
• Axial-DeepLab
• UPSNet
• EfficientPS
• MS-COCO
• GrabCut
• U-Net
• pix2pix
• CyCADA
• BERT
• SimCLR
• CycleGAN
• KITTI
• YOLACT++
• SegNet

This page was built for publication: Semantic Image Segmentation: Two Decades of Research

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5046690)