mlsanityData to 14 Oct 2026

Domain Generalization for Semantic Segmentation: A Survey

arXiv 2510.03540 ↗First posted 3 Oct 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The generalization of deep neural networks to unknown domains is a major challenge despite their tremendous progress in recent years. For this reason, the dynamic area of domain generalization (DG) has emerged. In contrast to unsupervised domain adaptation, there is no access to or knowledge about the target domains, and DG methods aim to generalize across multiple different unseen target domains. Domain generalization is particularly relevant for the task semantic segmentation which is used in several areas such as biomedicine or automated driving. This survey provides a comprehensive overview of the rapidly evolving topic of domain generalized semantic segmentation. We cluster and review existing approaches and identify the paradigm shift towards foundation-model-based domain generalization. Finally, we provide an extensive performance comparison of all approaches, which highlights the significant influence of foundation models on domain generalization. This survey seeks to advance domain generalization research and inspire scientists to explore new research directions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 58 of its 77 references that are in the map. First posted on arXiv 3 Oct 2025.

Builds on

58 of 77 references.

References · 58

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2023Segment Anythingcited by 8,234
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  8. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  10. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  11. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  12. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
38 more
  1. 2024VMamba: Visual State Space Modelcited by 969
  2. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  3. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  4. 2021Domain Generalization: A Surveycited by 764
  5. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  6. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 364
  7. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  8. 2017Toward Multimodal Image-to-Image Translationcited by 296
  9. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 246
  10. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 215
  11. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 177
  12. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 164
  13. 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
  14. 2019Switchable Whitening for Deep Representation Learningcited by 106
  15. 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 89
  16. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
  17. 2023Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentationcited by 83
  18. 2022Semantic-Aware Domain Generalized Segmentationcited by 79
  19. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 76
  20. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 70
  21. 2021Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentationcited by 57
  22. 2022Pin the Memory: Learning to Generalize Semantic Segmentationcited by 49
  23. 2023DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Controlcited by 45
  24. 2022PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalizationcited by 39
  25. 2023Collaborating Foundation Models for Domain Generalized Semantic Segmentationcited by 34
  26. 2023Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentationcited by 30
  27. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  28. 2023A Simple Recipe for Language-guided Domain Generalized Segmentationcited by 28
  29. 2023Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentationcited by 28
  30. 2023Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentationcited by 26
  31. 2021WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentationcited by 25
  32. 2023Texture Learning Domain Randomization for Domain Generalized Segmentationcited by 24
  33. 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentationcited by 24
  34. 2024Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentationcited by 22
  35. 2024Textual Query-Driven Mask Transformer for Domain Generalized Segmentationcited by 21
  36. 2023Domain Generalization via Balancing Training Difficulty and Model Capabilitycited by 20
  37. 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learningcited by 20
  38. 2024Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learningcited by 18

50 most cited of 58 All 58 (JSON)

Built on by

Not cited yet.