mlsanityData to 7 Oct 2026

Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

arXiv 2207.10667 ↗First posted 21 Jul 2022cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) aims at reducing the domain gap between training and testing data and is, in most cases, carried out in offline manner. However, domain changes may occur continuously and unpredictably during deployment (e.g. sudden weather changes). In such conditions, deep neural networks witness dramatic drops in accuracy and offline adaptation may not be enough to contrast it. In this paper, we tackle Online Domain Adaptation (OnDA) for semantic segmentation. We design a pipeline that is robust to continuous domain shifts, either gradual or sudden, and we evaluate it in the case of rainy and foggy scenarios. Our experiments show that our framework can effectively adapt to new domains during deployment, while not being affected by catastrophic forgetting of the previous domains.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 50 of its 63 references that are in the map. First posted on arXiv 21 Jul 2022.

Builds on

50 of 63 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  7. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  8. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  9. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  10. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  11. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  12. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
38 more
  1. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  2. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  3. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  4. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  5. 2018Born Again Neural Networkscited by 539
  6. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  7. 2019Confidence Regularized Self-Trainingcited by 418
  8. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  9. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  10. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  11. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  12. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  13. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  14. 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
  15. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  16. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  17. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  18. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  19. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  20. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  21. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  22. 2017No More Discrimination: Cross City Adaptation of Road Scene Segmenterscited by 110
  23. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  24. 2018Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understandingcited by 98
  25. 2019DADA: Depth-aware Domain Adaptation in Semantic Segmentationcited by 97
  26. 2015The Fast Bilateral Solvercited by 86
  27. 2018Real-time self-adaptive deep stereocited by 80
  28. 2019Open Compound Domain Adaptationcited by 76
  29. 2019Unsupervised Scene Adaptation with Memory Regularization in vivocited by 57
  30. 2020Rain rendering for evaluating and improving robustness to bad weathercited by 56
  31. 2017Incremental Adversarial Domain Adaptation for Continually Changing Environmentscited by 52
  32. 2019ACE: Adapting to Changing Environments for Semantic Segmentationcited by 44
  33. 2020Unsupervised Model Adaptation for Continual Semantic Segmentationcited by 42
  34. 2020Gradient Regularized Contrastive Learning for Continual Domain Adaptationcited by 35
  35. 2019Unsupervised Domain Adaptation via Regularized Conditional Alignmentcited by 34
  36. 2020Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representationscited by 24
  37. 2020Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replaycited by 19
  38. 2021Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundariescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 5; 2025: 4; 2026: 1.

16 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  3. 2023Test-Time Training on Video Streamscited by 37
  4. 2024Unified Language-driven Zero-shot Domain Adaptationcited by 30
  5. 2023To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentationcited by 14
  6. 2023DEJA VU: Continual Model Generalization For Unseen Domainscited by 13
  7. 2024Federated Online Adaptation for Deep Stereocited by 12
  8. 2025Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentationcited by 7
  9. 2023Online Distillation with Continual Learning for Cyclic Domain Shiftscited by 6
  10. 2024Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detectioncited by 5
  11. 2025Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regressioncited by 1
  12. 2025Improvise, Adapt, Overcome -- Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imagingcited by 1
4 more
  1. 2024CONTRAST: Continual Multi-source Adaptation to Dynamic Distributionscited by 0
  2. 2024DAWA: Dynamic Ambiguity-Wise Adaptation for Real-Time Domain Adaptive Semantic Segmentationcited by 0
  3. 2025Uncertainty-aware Test-Time Training (UT3) for Efficient On-the-fly Domain Adaptive Dense Regressioncited by 0
  4. 2026When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentationcited by 0