mlsanityData to 7 Oct 2026

Cross-Region Domain Adaptation for Class-level Alignment

arXiv 2109.06422 ↗First posted 14 Sep 2021cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation requires a lot of training data, which necessitates costly annotation. There have been many studies on unsupervised domain adaptation (UDA) from one domain to another, e.g., from computer graphics to real images. However, there is still a gap in accuracy between UDA and supervised training on native domain data. It is arguably attributable to class-level misalignment between the source and target domain data. To cope with this, we propose a method that applies adversarial training to align two feature distributions in the target domain. It uses a self-training framework to split the image into two regions (i.e., trusted and untrusted), which form two distributions to align in the feature space. We term this approach cross-region adaptation (CRA) to distinguish from the previous methods of aligning different domain distributions, which we call cross-domain adaptation (CDA). CRA can be applied after any CDA method. Experimental results show that this always improves the accuracy of the combined CDA method, having updated the state-of-the-art.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 14 Sep 2021.

Builds on

33 of 38 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2016Pyramid Scene Parsing Networkcited by 2,472
  8. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  9. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  10. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  11. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  12. 2018Dual Attention Network for Scene Segmentationcited by 1,001
21 more
  1. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  2. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  3. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  4. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  5. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  6. 2019Confidence Regularized Self-Trainingcited by 418
  7. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  8. 2018Context Encoding for Semantic Segmentationcited by 289
  9. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  10. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  11. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  12. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  13. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  14. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  15. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  16. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  17. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  18. 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
  19. 2018Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsingcited by 105
  20. 2019DADA: Depth-aware Domain Adaptation in Semantic Segmentationcited by 97
  21. 2020ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentationcited by 27

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 0; 2025: 2.

8 papers.

  1. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  2. 2022CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentationcited by 13
  3. 2025CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddingscited by 7
  4. 2022Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentationcited by 4
  5. 2023Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentationcited by 4
  6. 2025Test-Time Optimization for Domain Adaptive Open Vocabulary Segmentationcited by 3
  7. 20233D GANs and Latent Space: A comprehensive surveycited by 1
  8. 2022Rethinking Unsupervised Domain Adaptation for Semantic Segmentationcited by 0