mlsanityData to 7 Oct 2026

Learning to Adapt Structured Output Space for Semantic Segmentation

arXiv 1802.10349 ↗First posted 28 Feb 2018cs.CVcited by 584

Not on the map. Why?

Abstract (arXiv)

Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to the target domain is of great interest. In this paper, we propose an adversarial learning method for domain adaptation in the context of semantic segmentation. Considering semantic segmentations as structured outputs that contain spatial similarities between the source and target domains, we adopt adversarial learning in the output space. To further enhance the adapted model, we construct a multi-level adversarial network to effectively perform output space domain adaptation at different feature levels. Extensive experiments and ablation study are conducted under various domain adaptation settings, including synthetic-to-real and cross-city scenarios. We show that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.

Key facts. Cited by 584 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 169; 2022: 153; 2023: 113; 2024: 86; 2025: 45; 2026: 18.

584 papers.

Sort:

By area:

  1. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  2. 2022Continual Test-Time Domain Adaptationcited by 520
  3. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  4. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  5. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 259
  6. 2022Contrastive Test-Time Adaptationcited by 258
  7. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  8. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  9. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 176
  10. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  11. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
  12. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
38 more
  1. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  2. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  3. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  4. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  5. 2023DREAM: Efficient Dataset Distillation by Representative Matchingcited by 93
  6. 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 88
  7. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
  8. 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
  9. 2021Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentationcited by 81
  10. 2021DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentationcited by 80
  11. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  12. 2021PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Trainingcited by 80
  13. 2022OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mappingcited by 80
  14. 2021Context-Aware Mixup for Domain Adaptive Semantic Segmentationcited by 79
  15. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  16. 2022Semantic-Aware Domain Generalized Segmentationcited by 78
  17. 2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
  18. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
  19. 2021STEP: Segmenting and Tracking Every Pixelcited by 72
  20. 2022Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentationcited by 71
  21. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
  22. 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
  23. 2023On Pitfalls of Test-Time Adaptationcited by 63
  24. 2022PODA: Prompt-driven Zero-shot Domain Adaptationcited by 60
  25. 2021ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 57
  26. 2022Transferability in Deep Learning: A Surveycited by 57
  27. 2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
  28. 2021Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentationcited by 56
  29. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 56
  30. 2023Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networkscited by 55
  31. 2024Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Modelscited by 55
  32. 2021Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Typescited by 54
  33. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  34. 2021DINE: Domain Adaptation from Single and Multiple Black-box Predictorscited by 51
  35. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  36. 2021Test-time Batch Statistics Calibration for Covariate Shiftcited by 50
  37. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  38. 2021From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimationcited by 48

50 most cited of 584 All 584 (JSON)