mlsanityData to 14 Oct 2026

Self-supervised Augmentation Consistency for Adapting Semantic Segmentation

arXiv 2105.00097 ↗First posted 30 Apr 2021cs.CV cs.LGcited by 149

Not on the map. Why?

Abstract (arXiv)

We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. In contrast to previous work, we abandon the use of computationally involved adversarial objectives, network ensembles and style transfer. Instead, we employ standard data augmentation techniques - photometric noise, flipping and scaling - and ensure consistency of the semantic predictions across these image transformations. We develop this principle in a lightweight self-supervised framework trained on co-evolving pseudo labels without the need for cumbersome extra training rounds. Simple in training from a practitioner's standpoint, our approach is remarkably effective. We achieve significant improvements of the state-of-the-art segmentation accuracy after adaptation, consistent both across different choices of the backbone architecture and adaptation scenarios.

Key facts. Cited by 149 papers in the map (data through 14 Oct 2026). Builds on 71 of its 99 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

71 of 99 references.

References · 71

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  7. 2017On Calibration of Modern Neural Networkscited by 4,960
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  9. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  11. 2015Continuous control with deep reinforcement learningcited by 3,407
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
38 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2016Pyramid Scene Parsing Networkcited by 2,479
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  8. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  9. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  10. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,209
  11. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  12. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  13. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  14. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  15. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  16. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  17. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  18. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  19. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  20. 2019Confidence Regularized Self-Trainingcited by 419
  21. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  22. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 300
  23. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  24. 2014Learning with Pseudo-Ensemblescited by 241
  25. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  26. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  27. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  28. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 177
  29. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  30. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  31. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  32. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  33. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  34. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
  35. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  36. 2017No More Discrimination: Cross City Adaptation of Road Scene Segmenterscited by 111
  37. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  38. 2019All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentationcited by 104

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 36; 2023: 45; 2024: 31; 2025: 17; 2026: 7.

149 papers.

Sort:

By area:

  1. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  2. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 178
  3. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  4. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
  5. 2021Context-Aware Mixup for Domain Adaptive Semantic Segmentationcited by 79
  6. 2022Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentationcited by 47
  7. 2021ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenationcited by 41
  8. 2022PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentationcited by 41
  9. 2023All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenescited by 41
  10. 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
  11. 2022Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentationcited by 40
  12. 2023One-shot Unsupervised Domain Adaptation with Personalized Diffusion Modelscited by 35
38 more
  1. 2024Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentationcited by 34
  2. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  3. 2022Deliberated Domain Bridging for Domain Adaptive Semantic Segmentationcited by 31
  4. 2021Self-Adversarial Disentangling for Specific Domain Adaptationcited by 29
  5. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  6. 2024360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypescited by 28
  7. 2023FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understandingcited by 27
  8. 2021Dense Unsupervised Learning for Video Segmentationcited by 26
  9. 2021Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understandingcited by 26
  10. 2023Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentationcited by 26
  11. 2023Balancing Logit Variation for Long-tailed Semantic Segmentationcited by 26
  12. 2021Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 25
  13. 2021UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimationcited by 25
  14. 2022Learning from Future: A Novel Self-Training Framework for Semantic Segmentationcited by 21
  15. 2021Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Surveycited by 19
  16. 2023DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic Segmentationcited by 19
  17. 2024FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classificationcited by 19
  18. 2023EDAPS: Enhanced Domain-Adaptive Panoptic Segmentationcited by 17
  19. 2023Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environmentscited by 16
  20. 2023Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinementcited by 16
  21. 2022Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentationcited by 15
  22. 2024Training-Free Model Merging for Multi-target Domain Adaptationcited by 15
  23. 2023LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptationcited by 14
  24. 2022DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentationcited by 13
  25. 2023FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understandingcited by 13
  26. 2024MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentationcited by 13
  27. 2025Feed-Forward SceneDINO for Unsupervised Semantic Scene Completioncited by 13
  28. 2022Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teachercited by 12
  29. 2024CARLA Drone: Monocular 3D Object Detection from a Different Perspectivecited by 12
  30. 2021AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentationcited by 11
  31. 2022Domain Adaptive Video Segmentation via Temporal Pseudo Supervisioncited by 11
  32. 2022CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Carscited by 11
  33. 2023Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentationcited by 11
  34. 2023Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memorycited by 11
  35. 2024Exploring the Benefits of Vision Foundation Models for Unsupervised Domain Adaptationcited by 11
  36. 2025Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptationcited by 11
  37. 2023Augmentation-based Domain Generalization for Semantic Segmentationcited by 10
  38. 2025Scene-Centric Unsupervised Panoptic Segmentationcited by 10

50 most cited of 149 All 149 (JSON)