mlsanityData to 7 Oct 2026

Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation

arXiv 2108.02376 ↗First posted 5 Aug 2021cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation is a crucial image understanding task, where each pixel of image is categorized into a corresponding label. Since the pixel-wise labeling for ground-truth is tedious and labor intensive, in practical applications, many works exploit the synthetic images to train the model for real-word image semantic segmentation, i.e., Synthetic-to-Real Semantic Segmentation (SRSS). However, Deep Convolutional Neural Networks (CNNs) trained on the source synthetic data may not generalize well to the target real-world data. In this work, we propose two simple yet effective texture randomization mechanisms, Global Texture Randomization (GTR) and Local Texture Randomization (LTR), for Domain Generalization based SRSS. GTR is proposed to randomize the texture of source images into diverse unreal texture styles. It aims to alleviate the reliance of the network on texture while promoting the learning of the domain-invariant cues. In addition, we find the texture difference is not always occurred in entire image and may only appear in some local areas. Therefore, we further propose a LTR mechanism to generate diverse local regions for partially stylizing the source images. Finally, we implement a regularization of Consistency between GTR and LTR (CGL) aiming to harmonize the two proposed mechanisms during training. Extensive experiments on five publicly available datasets (i.e., GTA5, SYNTHIA, Cityscapes, BDDS and Mapillary) with various SRSS settings (i.e., GTA5/SYNTHIA to Cityscapes/BDDS/Mapillary) demonstrate that the proposed method is superior to the state-of-the-art methods for domain generalization based SRSS.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 58 of its 84 references that are in the map. First posted on arXiv 5 Aug 2021.

Builds on

58 of 84 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2017Mask R-CNNcited by 7,259
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2016Pyramid Scene Parsing Networkcited by 2,472
  11. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  12. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
38 more
  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  2. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  3. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  5. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  6. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  7. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  8. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  9. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  10. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  11. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  12. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  13. 2013Domain Generalization via Invariant Feature Representationcited by 622
  14. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  15. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  16. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  17. 2017Universal Style Transfer via Feature Transformscited by 352
  18. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  19. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  20. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  21. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  22. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 245
  23. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  24. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  25. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  26. 2017Image to Image Translation for Domain Adaptationcited by 171
  27. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  28. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  29. 2017Dataset Augmentation in Feature Spacecited by 124
  30. 2017No More Discrimination: Cross City Adaptation of Road Scene Segmenterscited by 110
  31. 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
  32. 2019Switchable Whitening for Deep Representation Learningcited by 105
  33. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  34. 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
  35. 2018Decorrelated Batch Normalizationcited by 83
  36. 2017AutoDIAL: Automatic DomaIn Alignment Layerscited by 75
  37. 2017Smart Augmentation - Learning an Optimal Data Augmentation Strategycited by 54
  38. 2017A Bayesian Data Augmentation Approach for Learning Deep Modelscited by 50

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 21; 2024: 7; 2025: 18; 2026: 5.

56 papers.

Sort:

By area:

  1. 2023Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentationcited by 82
  2. 2022Semantic-Aware Domain Generalized Segmentationcited by 78
  3. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
  4. 2023DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Controlcited by 44
  5. 2023Collaborating Foundation Models for Domain Generalized Semantic Segmentationcited by 33
  6. 2023HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentationcited by 31
  7. 2023Prompting Diffusion Representations for Cross-Domain Semantic Segmentationcited by 30
  8. 2023Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentationcited by 29
  9. 2023Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentationcited by 27
  10. 2023Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentationcited by 26
  11. 2023Texture Learning Domain Randomization for Domain Generalized Segmentationcited by 23
  12. 2022Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalizationcited by 22
38 more
  1. 2024SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learningcited by 22
  2. 2024Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentationcited by 21
  3. 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learningcited by 20
  4. 2023Unsupervised Domain Adaptation via Domain-Adaptive Diffusioncited by 19
  5. 2023Domain Generalization via Balancing Training Difficulty and Model Capabilitycited by 19
  6. 2024Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learningcited by 17
  7. 2025FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentationcited by 15
  8. 2023Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentationcited by 14
  9. 2024Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformationcited by 13
  10. 2023Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learningcited by 11
  11. 2023Augmentation-based Domain Generalization for Semantic Segmentationcited by 10
  12. 2023Informative Data Mining for One-Shot Cross-Domain Semantic Segmentationcited by 7
  13. 2024Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentationcited by 7
  14. 2023IBAFormer: Intra-batch Attention Transformer for Domain Generalized Semantic Segmentationcited by 6
  15. 2025Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentationcited by 6
  16. 2023DARNet: Bridging Domain Gaps in Cross-Domain Few-Shot Segmentation with Dynamic Adaptationcited by 5
  17. 2024Diffusion Features to Bridge Domain Gap for Semantic Segmentationcited by 5
  18. 2023Adaptive Texture Filtering for Single-Domain Generalized Segmentationcited by 3
  19. 2021Content Preserving Image Translation with Texture Co-occurrence and Spatial Self-Similarity for Texture Debiasing and Domain Adaptationcited by 2
  20. 2025Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Modelscited by 2
  21. 2023Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentationcited by 1
  22. 2024Semantic-Rearrangement-Based Multi-Level Alignment for Domain Generalized Segmentationcited by 1
  23. 2025What is the Added Value of UDA in the VFM Era?cited by 1
  24. 2025LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentationcited by 1
  25. 2025Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentationcited by 1
  26. 2025Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentationcited by 1
  27. 2026Local Precise Refinement: A Dual-Gated Mixture-of-Experts for Enhancing Foundation Model Generalization against Spectral Shiftscited by 1
  28. 2022A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentationcited by 0
  29. 2023Learning to Augment: Hallucinating Data for Domain Generalized Segmentationcited by 0
  30. 2025Depth-Sensitive Soft Suppression with RGB-D Inter-Modal Stylization Flow for Domain Generalization Semantic Segmentationcited by 0
  31. 2025Set Pivot Learning: Redefining Generalized Segmentation with Vision Foundation Modelscited by 0
  32. 2025Multi-Granularity Feature Calibration via VFM for Domain Generalized Semantic Segmentationcited by 0
  33. 2025IELDG: Suppressing Domain-Specific Noise with Inverse Evolution Layers for Domain Generalized Semantic Segmentationcited by 0
  34. 2025SynthGenNet: a self-supervised approach for test-time generalization using synthetic multi-source domain mixing of street view imagescited by 0
  35. 2025FRIEREN: Federated Learning with Vision-Language Regularization for Segmentationcited by 0
  36. 2025Domain Generalization for Semantic Segmentation: A Surveycited by 0
  37. 2025Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentationcited by 0
  38. 2025SAGE: Style-Adaptive Generalization for Privacy-Constrained Semantic Segmentation Across Domainscited by 0

50 most cited of 56 All 56 (JSON)