mlsanityData to 7 Oct 2026

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization

arXiv 2112.00463 ↗First posted 1 Dec 2021cs.CVcited by 131

Not on the map. Why?

Abstract (arXiv)

Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually require a large amount of labeled or unlabeled data from the shifted domain. This can be a hurdle in fields which require continuous dynamic adaptation or suffer from scarcity of data, e.g. autonomous driving in challenging weather conditions. To address this problem of continuous adaptation to distribution shifts, we propose Dynamic Unsupervised Adaptation (DUA). By continuously adapting the statistics of the batch normalization layers we modify the feature representations of the model. We show that by sequentially adapting a model with only a fraction of unlabeled data, a strong performance gain can be achieved. With even less than 1% of unlabeled data from the target domain, DUA already achieves competitive results to strong baselines. In addition, the computational overhead is minimal in contrast to previous approaches. Our approach is simple, yet effective and can be applied to any architecture which uses batch normalization as one of its components. We show the utility of DUA by evaluating it on a variety of domain adaptation datasets and tasks including object recognition, digit recognition and object detection.

Key facts. Cited by 131 papers in the map (data through 7 Oct 2026). Builds on 54 of its 78 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

54 of 78 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2016Wide Residual Networkscited by 3,057
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  10. 2018YOLOv3: An Incremental Improvementcited by 2,652
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
38 more
  1. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  2. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  3. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  4. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  5. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  6. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  7. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  8. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  9. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  10. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  11. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  12. 2018How Does Batch Normalization Help Optimization?cited by 355
  13. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  14. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  15. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  16. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  17. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 235
  18. 2016Coupled Generative Adversarial Networkscited by 216
  19. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  20. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  21. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  22. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  23. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  24. 2019Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detectioncited by 122
  25. 2019Unsupervised Domain Adaptation through Self-Supervisioncited by 116
  26. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  27. 2019Multi-adversarial Faster-RCNN for Unrestricted Object Detectioncited by 111
  28. 2017No More Discrimination: Cross City Adaptation of Road Scene Segmenterscited by 110
  29. 2019Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approachcited by 103
  30. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  31. 2020Cross-domain Object Detection through Coarse-to-Fine Feature Adaptationcited by 82
  32. 2017AutoDIAL: Automatic DomaIn Alignment Layerscited by 75
  33. 2021Cross-domain Contrastive Learning for Unsupervised Domain Adaptationcited by 75
  34. 2017Unsupervised Domain Adaptation with Similarity Learningcited by 73
  35. 2019Physics-Based Rendering for Improving Robustness to Raincited by 49
  36. 2019Multi-level Domain Adaptive learning for Cross-Domain Detectioncited by 30
  37. 2019Batch Normalization is a Cause of Adversarial Vulnerabilitycited by 28
  38. 2021Robustness of Object Detectors in Degrading Weather Conditionscited by 28

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 9; 2023: 35; 2024: 42; 2025: 28; 2026: 17.

131 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 102
  3. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  4. 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalizationcited by 100
  5. 2023Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineeringcited by 91
  6. 2023Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correctioncited by 65
  7. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  8. 2023CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classificationcited by 46
  9. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 43
  10. 2023Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objectscited by 40
  11. 2022ActMAD: Activation Matching to Align Distributions for Test-Time-Trainingcited by 38
  12. 2024Dual Prototype Evolving for Test-Time Generalization of Vision-Language Modelscited by 36
38 more
  1. 2022Video Test-Time Adaptation for Action Recognitioncited by 35
  2. 2024DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptationcited by 33
  3. 2023Prompting Diffusion Representations for Cross-Domain Semantic Segmentationcited by 30
  4. 2023Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentationcited by 29
  5. 2023ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalizationcited by 28
  6. 2023Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigationcited by 25
  7. 2023TEA: Test-time Energy Adaptationcited by 25
  8. 2022MATE: Masked Autoencoders are Online 3D Test-Time Learnerscited by 23
  9. 2023Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptationcited by 23
  10. 2022SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognitioncited by 21
  11. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  12. 2025Bayesian Test-Time Adaptation for Vision-Language Modelscited by 21
  13. 2024T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memorycited by 20
  14. 2024OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptationcited by 17
  15. 2023DARTH: Holistic Test-time Adaptation for Multiple Object Trackingcited by 15
  16. 2023Effective Restoration of Source Knowledge in Continual Test Time Adaptationcited by 15
  17. 2023What, How, and When Should Object Detectors Update in Continually Changing Test Domains?cited by 15
  18. 2023ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentationcited by 14
  19. 2024HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generationcited by 14
  20. 2022Learning Instance-Specific Adaptation for Cross-Domain Segmentationcited by 13
  21. 2023Evaluation of Test-Time Adaptation Under Computational Time Constraintscited by 13
  22. 2022Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Surveycited by 12
  23. 2023Uncovering Adversarial Risks of Test-Time Adaptationcited by 12
  24. 2024PASS:Test-Time Prompting to Adapt Styles and Semantic Shapes in Medical Image Segmentationcited by 12
  25. 2023Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memorycited by 11
  26. 2024CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformationcited by 11
  27. 2024Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentationcited by 11
  28. 2023Unraveling Batch Normalization for Realistic Test-Time Adaptationcited by 10
  29. 2024ConvLoRA and AdaBN based Domain Adaptation via Self-Trainingcited by 10
  30. 2023Bag of Tricks for Fully Test-Time Adaptationcited by 8
  31. 2024Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptationcited by 8
  32. 2024ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Trainingcited by 8
  33. 2025E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Modelscited by 8
  34. 2025TTRV: Test-Time Reinforcement Learning for Vision Language Modelscited by 8
  35. 2024Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlationcited by 7
  36. 2024Decoupled Prototype Learning for Reliable Test-Time Adaptationcited by 7
  37. 2024Learning Visual Conditioning Tokens to Correct Domain Shift for Fully Test-time Adaptationcited by 7
  38. 2024Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averagingcited by 7

50 most cited of 131 All 131 (JSON)