• Home
  • Search
  • Unsupervised Domain Adaptation for Semantic Segmentation with Global and Local Consistency
  • https://doi.org/10.1007/978-3-031-20497-5_13Copy DOI Icon

Unsupervised Domain Adaptation for Semantic Segmentation with Global and Local Consistency

  • Jan 1, 2022
  • Xiangxuan Shan +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Abstract Unsupervised domain adaptation(UDA) for semantic segmentation aims to learn from labeled synthetic data to segment the unlabeled real data. Many recent methods use generative networks to acquire real-like images for mitigating domain shift. However, these methods only ensure global style consistency between two domains and fail to impose pixel-wise constraint which is also referred to as local content consistency. To address the above problem, we propose a global and local consistency network to reduce the domain gap in unsupervised domain adaptation for semantic segmentation. To this end, we first constrain global style consistency through a generative adversarial network to acquire real-like latent domain images. Then we enhance local content consistency based on pixel-wise entropy minimization. Experimental results show that our method has superiority over other competitive methods on GTA5 \(\rightarrow \) Cityscapes.KeywordsUnsupervised domain adaptationSemantic segmentationStyle transfer

Similar Papers
  • Research Article
  • Citations42

Unsupervised Domain Adaptation for Semantic Segmentation by Content Transfer

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Suhyeon Lee +3
  • Conference Article
  • Citations38

Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation

  • Oct 17, 2021
  • Mucong Ye +3
  • Conference Article
  • Citations20

Source Free Domain Adaptation for Semantic Segmentation via Distribution Transfer and Adaptive Class-Balanced Self-Training

  • Jul 18, 2022
  • Cheng-Yu Yang +2
  • Book Chapter

Unsupervised Domain Adaptation for Semantic Segmentation with Unstable Category Feature Enhancement

  • Oct 21, 2025
  • Frontiers in artificial intelligence and applications
  • Xuewei Li +5
  • Book Chapter
  • Citations14

Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

  • Jan 01, 2022
  • Theodoros Panagiotakopoulos +3
  • Research Article
  • Citations17

DASRSNet: Multitask Domain Adaptation for Super-Resolution-Aided Semantic Segmentation of Remote Sensing Images

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yuxiang Cai +4
  • Conference Article
  • Citations13

Towards Unsupervised Online Domain Adaptation for Semantic Segmentation

  • Jan 01, 2022
  • Yevhen Kuznietsov +2
  • Research Article
  • Citations27

Knowledge based domain adaptation for semantic segmentation

  • Dec 27, 2019
  • Knowledge-Based Systems
  • Yuxiao Zhang +3
  • Book Chapter
  • Citations1

Consistency Regularization for Unsupervised Domain Adaptation in Semantic Segmentation

  • Jan 01, 2022
  • Sebastian Scherer +2
  • Conference Article

Effect of Loss Functions on Domain Adaptation in Semantic Segmentation

  • Jun 09, 2021
  • Kirman Serdar +2
  • Research Article
  • Citations31

Joint Adversarial Learning for Domain Adaptation in Semantic Segmentation

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Yixin Zhang +1
  • Conference Article
  • Citations3

Task-in-all Domain Adaptation for Semantic Segmentation

  • Dec 01, 2019
  • Tianyi Zhang +5
  • Conference Article
  • Citations65

StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization

  • Jun 01, 2020
  • Onur Tasar +4
  • Conference Article
  • Citations60

Unsupervised Domain Adaptation for Semantic Segmentation of Urban Scenes

  • Jun 01, 2019
  • Matteo Biasetton +3
  • Conference Article
  • Citations4

Domain Adaptation for Semantic Segmentation of Aerial Imagery Using Cycle-Consistent Adversarial Networks

  • Sep 26, 2020
  • Fabian Schenkel +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.