mlsanityData to 7 Oct 2026

SPIGAN: Privileged Adversarial Learning from Simulation

arXiv 1810.03756 ↗First posted 9 Oct 2018cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

Deep Learning for Computer Vision depends mainly on the source of supervision.Photo-realistic simulators can generate large-scale automatically labeled syntheticdata, but introduce a domain gap negatively impacting performance. We propose anew unsupervised domain adaptation algorithm, called SPIGAN, relying on Sim-ulator Privileged Information (PI) and Generative Adversarial Networks (GAN).We use internal data from the simulator as PI during the training of a target tasknetwork. We experimentally evaluate our approach on semantic segmentation. Wetrain the networks on real-world Cityscapes and Vistas datasets, using only unla-beled real-world images and synthetic labeled data with z-buffer (depth) PI fromthe SYNTHIA dataset. Our method improves over no adaptation and state-of-the-art unsupervised domain adaptation techniques.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 7; 2023: 12; 2024: 8; 2025: 3; 2026: 1.

47 papers.

Sort:

By area:

  1. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  2. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  3. 2021Learning to Track with Object Permanencecited by 117
  4. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  5. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  6. 2021Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentationcited by 40
  7. 2021Geometric Unsupervised Domain Adaptation for Semantic Segmentationcited by 33
  8. 2021Learning to Relate Depth and Semantics for Unsupervised Domain Adaptationcited by 32
  9. 2021BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentationcited by 31
  10. 2021Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approachescited by 30
  11. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  12. 2023FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understandingcited by 27
35 more
  1. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  2. 2021Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 25
  3. 2021Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentationcited by 16
  4. 2021Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translationcited by 15
  5. 2021Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentationcited by 13
  6. 2024MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentationcited by 13
  7. 2021Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentationcited by 12
  8. 2022Continual BatchNorm Adaptation (CBNA) for Semantic Segmentationcited by 12
  9. 2021Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptationcited by 11
  10. 2022CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Carscited by 11
  11. 2023Augmentation-based Domain Generalization for Semantic Segmentationcited by 10
  12. 2023Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptationcited by 9
  13. 2024EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understandingcited by 6
  14. 2024Towards Interpretable Physical-Conceptual Catchment-Scale Hydrological Modeling using the Mass-Conserving-Perceptroncited by 4
  15. 2024Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentationcited by 4
  16. 2022Geometry-Aware Network for Domain Adaptive Semantic Segmentationcited by 3
  17. 2021Unsupervised Domain Adaptation from Axial to Short-Axis Multi-Slice Cardiac MR Images by Incorporating Pretrained Task Networkscited by 2
  18. 2021Improving Online Performance Prediction for Semantic Segmentationcited by 2
  19. 2023Learning Good Features to Transfer Across Tasks and Domainscited by 2
  20. 2023CROVIA: Seeing Drone Scenes from Car Perspective via Cross-View Adaptationcited by 2
  21. 2023CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentationcited by 2
  22. 2022Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentationcited by 1
  23. 2023HazardNet: Road Debris Detection by Augmentation of Synthetic Modelscited by 1
  24. 2023Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenationcited by 1
  25. 2024Energy-based Domain-Adaptive Segmentation with Depth Guidancecited by 1
  26. 2025Post-Convergence Sim-to-Real Policy Transfer: A Principled Alternative to Cherry-Pickingcited by 1
  27. 2025Sim2Real in endoscopy segmentation with a novel structure aware image translationcited by 1
  28. 2026PEPR: Privileged Event-based Predictive Regularization for Domain Generalizationcited by 1
  29. 2022Knowledge-Integrated Informed AI for National Securitycited by 0
  30. 2022ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDAcited by 0
  31. 2023Regularizing Self-training for Unsupervised Domain Adaptation via Structural Constraintscited by 0
  32. 2024Machine learning-based optimization workflow of the homogeneity of spunbond nonwovens with human validationcited by 0
  33. 2024Output-Constrained Decision Treescited by 0
  34. 2024A Study on Unsupervised Domain Adaptation for Semantic Segmentation in the Era of Vision-Language Modelscited by 0
  35. 2025Depth-Sensitive Soft Suppression with RGB-D Inter-Modal Stylization Flow for Domain Generalization Semantic Segmentationcited by 0