• Home
  • Search
  • Semantic Image Segmentation: Two Decades of Research
  • Cite Icon55
  • https://doi.org/10.1561/0600000095Copy DOI Icon

Semantic Image Segmentation: Two Decades of Research

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. This survey is an effort to summarize two decades of research in the field of SiS, where we propose a literature review of solutions starting from early historical methods followed by an overview of more recent deep learning methods including the latest trend of using transformers. We complement the review by discussing particular cases of the weak supervision and side machine learning techniques that can be used to improve the semantic segmentation such as curriculum, incremental or self-supervised learning. State-of-the-art SiS models rely on a large amount of annotated samples, which are more expensive to obtain than labels for tasks such as image classification. Since unlabeled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation (UDA) reached a broad success within the semantic segmentation community. Therefore, a second core contribution of this monograph is to summarize five years of a rapidly growing field, Domain Adaptation for Semantic Image Segmentation (DASiS) which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. In addition to providing a comprehensive survey on DASiS techniques, we unveil also newer trends such as multi-domain learning, domain generalization, domain incremental learning, test-time adaptation and source-free domain adaptation. Finally, we conclude this survey by describing datasets and benchmarks most widely used in SiS and DASiS and briefly discuss related tasks such as instance and panoptic image segmentation, as well as applications such as medical image segmentation. We hope that this monograph will provide researchers across academia and industry with a comprehensive reference guide and will help them in fostering new research directions in the field.

Similar Papers
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • PDF
  • Research Article
  • Citations10

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models

  • Jan 05, 2023
  • Sensors (Basel, Switzerland)
  • Jose L Gómez +2
  • Research Article
  • Citations13

Enhancing unsupervised domain adaptation by discriminative relevance regularization

  • Apr 17, 2020
  • Knowledge and Information Systems
  • Wenju Zhang +3
  • Research Article
  • Citations6

Gradient-based class weighting for unsupervised domain adaptation in dense prediction visual tasks

  • Oct 01, 2025
  • Pattern Recognition
  • Roberto Alcover-Couso +3
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Research Article
  • Citations57

A One-Stage Domain Adaptation Network With Image Alignment for Unsupervised Nighttime Semantic Segmentation.

  • Jan 01, 2023
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Xinyi Wu +3
  • Conference Article
  • Citations261

Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic Segmentation

  • Oct 01, 2019
  • Jaehoon Choi +2
  • Conference Article
  • Citations38

Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation

  • Oct 17, 2021
  • Mucong Ye +3
  • Research Article
  • Citations52

Transfer Beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation

  • Jul 01, 2022
  • IEEE Transactions on Intelligent Transportation Systems
  • Jiaming Zhang +5
  • Research Article
  • Citations19

Adversarial Learning Based Discriminative Domain Adaptation for Geospatial Image Analysis

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Nikhil Makkar +2
  • Research Article
  • Citations2

CSF: Closed-mask-guided semantic fusion method for semantic perception of unknown scenes

  • Sep 01, 2022
  • Pattern Recognition Letters
  • Minghong Chen +4
  • PDF
  • Research Article
  • Citations3

Active Bidirectional Self-Training Network for Cross-Domain Segmentation in Remote-Sensing Images

  • Jul 08, 2024
  • Remote Sensing
  • Zhujun Yang +5
  • PDF
  • Supplementary Content
  • Citations23

A Review on Recent Deep Learning-Based Semantic Segmentation for Urban Greenness Measurement

  • Mar 31, 2024
  • Sensors (Basel, Switzerland)
  • Doo Hong Lee +2
  • PDF
  • Research Article
  • Citations4

Source-free domain adaptation for semantic image segmentation using internal representations.

  • Jun 18, 2024
  • Frontiers in big data
  • Serban Stan +1
  • Research Article
  • Citations2

Domain adaptation for semantic segmentation of road scenes via two-stage alignment of traffic elements

  • Oct 18, 2024
  • Neurocomputing
  • Yuan Gao +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.