mlsanityData to 14 Oct 2026

Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentation

arXiv 2110.06685 ↗First posted 13 Oct 2021cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Although recent semantic segmentation methods have made remarkable progress, they still rely on large amounts of annotated training data, which are often infeasible to collect in the autonomous driving scenario. Previous works usually tackle this issue with Unsupervised Domain Adaptation (UDA), which entails training a network on synthetic images and applying the model to real ones while minimizing the discrepancy between the two domains. Yet, these techniques do not consider additional information that may be obtained from other tasks. Differently, we propose to exploit self-supervised monocular depth estimation to improve UDA for semantic segmentation. On one hand, we deploy depth to realize a plug-in component which can inject complementary geometric cues into any existing UDA method. We further rely on depth to generate a large and varied set of samples to Self-Train the final model. Our whole proposal allows for achieving state-of-the-art performance (58.8 mIoU) in the GTA5->CS benchmark benchmark. Code is available at https://github.com/CVLAB-Unibo/d4-dbst.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 62 of its 73 references that are in the map. First posted on arXiv 13 Oct 2021.

Builds on

62 of 73 references.

References · 62

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  9. 2014How transferable are features in deep neural networks?cited by 1,225
  10. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  11. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  12. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
38 more
  1. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  2. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  3. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  4. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  5. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  6. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  7. 2019Confidence Regularized Self-Trainingcited by 419
  8. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  9. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  10. 2017Dilated Residual Networkscited by 294
  11. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  12. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  13. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 243
  14. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  15. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  16. 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
  17. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 206
  18. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  19. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  20. 2017Image to Image Translation for Domain Adaptationcited by 171
  21. 2017Playing for Benchmarkscited by 169
  22. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  23. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  24. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  25. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  26. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  27. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  28. 2019Self-Supervised Monocular Depth Hintscited by 127
  29. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
  30. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  31. 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
  32. 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
  33. 2019All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentationcited by 104
  34. 2019Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approachcited by 103
  35. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  36. 2019DADA: Depth-aware Domain Adaptation in Semantic Segmentationcited by 97
  37. 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
  38. 2018Fully Convolutional Adaptation Networks for Semantic Segmentationcited by 75

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 8; 2024: 1; 2025: 0; 2026: 1.

13 papers.

Sort:

  1. 2022Source-free Depth for Object Pop-outcited by 52
  2. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  3. 2023Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Samplingcited by 19
  4. 2023Fully Self-Supervised Depth Estimation from Defocus Cluecited by 17
  5. 2023Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentationcited by 14
  6. 2023Bridging the Gap between Multi-focus and Multi-modal: A Focused Integration Framework for Multi-modal Image Fusioncited by 11
  7. 2023High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimationcited by 10
  8. 2023Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptationcited by 9
  9. 2022False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimationcited by 3
  10. 2022Cut-Paste Consistency Learning for Semi-Supervised Lesion Segmentationcited by 3
  11. 2023A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware designcited by 2
  12. 2024Energy-based Domain-Adaptive Segmentation with Depth Guidancecited by 1
1 more
  1. 2026GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depthcited by 1