mlsanityData to 7 Oct 2026

IDA: Informed Domain Adaptive Semantic Segmentation

arXiv 2303.02741 ↗First posted 5 Mar 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Mixup-based data augmentation has been validated to be a critical stage in the self-training framework for unsupervised domain adaptive semantic segmentation (UDA-SS), which aims to transfer knowledge from a well-annotated (source) domain to an unlabeled (target) domain. Existing self-training methods usually adopt the popular region-based mixup techniques with a random sampling strategy, which unfortunately ignores the dynamic evolution of different semantics across various domains as training proceeds. To improve the UDA-SS performance, we propose an Informed Domain Adaptation (IDA) model, a self-training framework that mixes the data based on class-level segmentation performance, which aims to emphasize small-region semantics during mixup. In our IDA model, the class-level performance is tracked by an expected confidence score (ECS). We then use a dynamic schedule to determine the mixing ratio for data in different domains. Extensive experimental results reveal that our proposed method is able to outperform the state-of-the-art UDA-SS method by a margin of 1.1 mIoU in the adaptation of GTA-V to Cityscapes and of 0.9 mIoU in the adaptation of SYNTHIA to Cityscapes.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 37 of its 41 references that are in the map. First posted on arXiv 5 Mar 2023.

Builds on

37 of 41 references.

References · 37

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  8. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  9. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  10. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  11. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  12. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
25 more
  1. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  2. 2019Confidence Regularized Self-Trainingcited by 418
  3. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  4. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  5. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  6. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  7. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  8. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  9. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  10. 2021K-Net: Towards Unified Image Segmentationcited by 211
  11. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  12. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  13. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  14. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  15. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  16. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  17. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  18. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  19. 2020A Survey on Negative Transfercited by 120
  20. 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
  21. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  22. 2019Unsupervised Scene Adaptation with Memory Regularization in vivocited by 57
  23. 2019An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentationcited by 48
  24. 2020Context-Aware Domain Adaptation in Semantic Segmentationcited by 36
  25. 2022CALI: Coarse-to-Fine ALIgnments Based Unsupervised Domain Adaptation of Traversability Prediction for Deployable Autonomous Navigationcited by 3

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 3.

8 papers.

  1. 2025FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Drivingcited by 5
  2. 2024Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentationcited by 4
  3. 2025Enhancing Large Vision Model in Street Scene Semantic Understanding through Leveraging Posterior Optimization Trajectorycited by 4
  4. 2025AFRDA: Attentive Feature Refinement for Domain Adaptive Semantic Segmentationcited by 2
  5. 2024Energy-based Domain-Adaptive Segmentation with Depth Guidancecited by 1
  6. 2024Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statisticscited by 1
  7. 2024ECAP: Extensive Cut-and-Paste Augmentation for Unsupervised Domain Adaptive Semantic Segmentationcited by 0
  8. 2024C^2DA: Contrastive and Context-aware Domain Adaptive Semantic Segmentationcited by 0