mlsanityData to 7 Oct 2026

Geometric Unsupervised Domain Adaptation for Semantic Segmentation

arXiv 2103.16694 ↗First posted 30 Mar 2021cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world performance. We propose to use self-supervised monocular depth estimation as a proxy task to bridge this gap and improve sim-to-real unsupervised domain adaptation (UDA). Our Geometric Unsupervised Domain Adaptation method (GUDA) learns a domain-invariant representation via a multi-task objective combining synthetic semantic supervision with real-world geometric constraints on videos. GUDA establishes a new state of the art in UDA for semantic segmentation on three benchmarks, outperforming methods that use domain adversarial learning, self-training, or other self-supervised proxy tasks. Furthermore, we show that our method scales well with the quality and quantity of synthetic data while also improving depth prediction.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 65 of its 82 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

65 of 82 references.

References · 65

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  6. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  7. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  8. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  9. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  10. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  11. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  12. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
38 more
  1. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  2. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  3. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  4. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  5. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  6. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  7. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  8. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  9. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  10. 2019Confidence Regularized Self-Trainingcited by 418
  11. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  12. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  13. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  14. 2020Virtual KITTI 2cited by 345
  15. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  16. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  17. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  18. 2016Learning Representations for Automatic Colorizationcited by 251
  19. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  20. 2015DeepStereo: Learning to Predict New Views from the World's Imagerycited by 185
  21. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  22. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  23. 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
  24. 2016Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptationcited by 162
  25. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  26. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  27. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  28. 2017Domain Adaptation for Visual Applications: A Comprehensive Surveycited by 127
  29. 2017Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenescited by 122
  30. 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
  31. 2019Unsupervised Domain Adaptation through Self-Supervisioncited by 116
  32. 2017Adversarial Dropout Regularizationcited by 106
  33. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  34. 2019DADA: Depth-aware Domain Adaptation in Semantic Segmentationcited by 97
  35. 2016Learning Dense Correspondence via 3D-guided Cycle Consistencycited by 91
  36. 2018Fully Convolutional Adaptation Networks for Semantic Segmentationcited by 75
  37. 2019Discriminative Adversarial Domain Adaptationcited by 74
  38. 2018Self-Supervised Model Adaptation for Multimodal Semantic Segmentationcited by 73

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 10; 2023: 11; 2024: 6; 2025: 3; 2026: 1.

33 papers.

Sort:

By area:

  1. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  2. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  3. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  4. 2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
  5. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  6. 2024Cross-View Completion Models are Zero-shot Correspondence Estimatorscited by 30
  7. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  8. 2023Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Modelcited by 29
  9. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  10. 2021Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 25
  11. 2022DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learningcited by 25
  12. 2022SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpointscited by 22
21 more
  1. 2022DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentationcited by 22
  2. 2023CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentationcited by 18
  3. 2023DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibriumcited by 16
  4. 2023Tracking through Containers and Occluders in the Wildcited by 15
  5. 2024MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentationcited by 13
  6. 2022Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learningcited by 12
  7. 2025Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusioncited by 12
  8. 2026AnyView: Synthesizing Any Novel View in Dynamic Scenescited by 12
  9. 2024GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusioncited by 6
  10. 2025Towards In-the-wild 3D Plane Reconstruction from a Single Imagecited by 6
  11. 2022Photo-realistic Neural Domain Randomizationcited by 5
  12. 2025Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentationcited by 3
  13. 2022Multi-view Monocular Depth and Uncertainty Prediction with Deep SfM in Dynamic Environmentscited by 2
  14. 2023MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentationcited by 2
  15. 2023Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentationcited by 2
  16. 2023Do More With What You Have: Transferring Depth-Scale from Labeled to Unlabeled Domainscited by 1
  17. 2023HQDec: Self-Supervised Monocular Depth Estimation Based on a High-Quality Decodercited by 1
  18. 2024MCDS-VSS: Moving Camera Dynamic Scene Video Semantic Segmentation by Filtering with Self-Supervised Geometry and Motioncited by 1
  19. 2022ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDAcited by 0
  20. 2024Enhancing AI Diagnostics: Autonomous Lesion Masking via Semi-Supervised Deep Learningcited by 0
  21. 2024FA-Depth: Toward Fast and Accurate Self-supervised Monocular Depth Estimationcited by 0