mlsanityData to 7 Oct 2026

Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data

arXiv 1909.00889 ↗First posted 2 Sep 2019cs.CVcited by 245

Not on the map. Why?

Abstract (arXiv)

We propose to harness the potential of simulation for the semantic segmentation of real-world self-driving scenes in a domain generalization fashion. The segmentation network is trained without any data of target domains and tested on the unseen target domains. To this end, we propose a new approach of domain randomization and pyramid consistency to learn a model with high generalizability. First, we propose to randomize the synthetic images with the styles of real images in terms of visual appearances using auxiliary datasets, in order to effectively learn domain-invariant representations. Second, we further enforce pyramid consistency across different "stylized" images and within an image, in order to learn domain-invariant and scale-invariant features, respectively. Extensive experiments are conducted on the generalization from GTA and SYNTHIA to Cityscapes, BDDS and Mapillary; and our method achieves superior results over the state-of-the-art techniques. Remarkably, our generalization results are on par with or even better than those obtained by state-of-the-art simulation-to-real domain adaptation methods, which access the target domain data at training time.

Key facts. Cited by 245 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 47; 2022: 62; 2023: 70; 2024: 31; 2025: 24; 2026: 11.

245 papers.

Sort:

By area:

  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  4. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  5. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  6. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  7. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
  8. 2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalizationcited by 144
  9. 2024Flow as the Cross-Domain Manipulation Interfacecited by 126
  10. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  11. 2021Model-Based Domain Generalizationcited by 103
  12. 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 88
38 more
  1. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  2. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  3. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  4. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 85
  5. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  6. 2023Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentationcited by 82
  7. 2021Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentationcited by 81
  8. 2023Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusioncited by 81
  9. 2022Semantic-Aware Domain Generalized Segmentationcited by 78
  10. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
  11. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
  12. 2022C-Mixup: Improving Generalization in Regressioncited by 57
  13. 2021Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentationcited by 56
  14. 2023Label-Free Liver Tumor Segmentationcited by 56
  15. 2023How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligencecited by 55
  16. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  17. 2022Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objectscited by 49
  18. 2022Pin the Memory: Learning to Generalize Semantic Segmentationcited by 48
  19. 2021Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalizationcited by 45
  20. 2021Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentationcited by 44
  21. 2023DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Controlcited by 44
  22. 2021Multi-Target Domain Adaptation with Collaborative Consistency Learningcited by 43
  23. 2021Source-Free Open Compound Domain Adaptation in Semantic Segmentationcited by 43
  24. 2022Deep Frequency Filtering for Domain Generalizationcited by 41
  25. 2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
  26. 2023A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidancecited by 40
  27. 2022ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networkscited by 39
  28. 2022PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalizationcited by 38
  29. 2021Feature-based Style Randomization for Domain Generalizationcited by 34
  30. 2021CrossNorm and SelfNorm for Generalization under Distribution Shiftscited by 33
  31. 2023Progressive Random Convolutions for Single Domain Generalizationcited by 33
  32. 2023Collaborating Foundation Models for Domain Generalized Semantic Segmentationcited by 33
  33. 2021Contrastive Syn-to-Real Generalizationcited by 32
  34. 2023HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentationcited by 31
  35. 2021Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environmentscited by 30
  36. 2023Prompting Diffusion Representations for Cross-Domain Semantic Segmentationcited by 30
  37. 2021Self-Adversarial Disentangling for Specific Domain Adaptationcited by 29
  38. 2023Neuron Structure Modeling for Generalizable Remote Physiological Measurementcited by 29

50 most cited of 245 All 245 (JSON)