mlsanityData to 7 Oct 2026

Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classification

arXiv 2502.10694 ↗First posted 15 Feb 2025cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance drops when the trained model is used in new data sets. Domain adaptation (DA) is a machine learning technique that aims to address this problem by reducing the differences between domains. This paper presents simulation-based algorithms of recent DA techniques, mainly related to unsupervised domain adaptation (UDA), where labels are available only in the source domain. Our study compares these techniques with public data sets and diverse characteristics, highlighting their respective strengths and drawbacks. For example, Safe Self-Refinement for Transformer-based DA (SSRT) achieved the highest accuracy (91.6%) in the office-31 data set during our simulations, however, the accuracy dropped to 72.4% in the Office-Home data set when using limited batch sizes. In addition to improving the reader's comprehension of recent techniques in DA, our study also highlights challenges and upcoming directions for research in this domain. The codes are available at https://github.com/AIPMLab/DomainAdaptation.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 58 of its 106 references that are in the map. First posted on arXiv 15 Feb 2025.

Builds on

58 of 106 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  9. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  10. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  11. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  12. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
38 more
  1. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  2. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  3. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  4. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  5. 2020A Survey on Visual Transformercited by 653
  6. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  7. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  8. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  9. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 590
  10. 2017VisDA: The Visual Domain Adaptation Challengecited by 432
  11. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  12. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  13. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  14. 2022Contrastive Test-Time Adaptationcited by 258
  15. 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
  16. 2020Domain Generalization using Causal Matchingcited by 224
  17. 2018Multi-Adversarial Domain Adaptationcited by 195
  18. 2017Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptationcited by 151
  19. 2020Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situationscited by 133
  20. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  21. 2018Partial Adversarial Domain Adaptationcited by 127
  22. 2020Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domainscited by 124
  23. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
  24. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  25. 2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
  26. 2020Domain Adaptation without Source Datacited by 88
  27. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  28. 2020Maximum Density Divergence for Domain Adaptationcited by 76
  29. 2022Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptationcited by 66
  30. 2021On Generating Transferable Targeted Perturbationscited by 65
  31. 2022Safe Self-Refinement for Transformer-based Domain Adaptationcited by 61
  32. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  33. 2021Source-Free Open Compound Domain Adaptation in Semantic Segmentationcited by 43
  34. 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
  35. 2019Transfer Learning with Dynamic Adversarial Adaptation Networkcited by 37
  36. 2023ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptationcited by 34
  37. 2022Out-of-Distribution Representation Learning for Time Series Classificationcited by 30
  38. 2019Discriminative Joint Probability Maximum Mean Discrepancy (DJP-MMD) for Domain Adaptationcited by 15

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025FAA-CLIP: Federated Adversarial Adaptation of CLIPcited by 5
  2. 2025Semi-Supervised Medical Image Segmentation via Dual Networkscited by 2
  3. 2025Domain Adaptation Techniques for Natural and Medical Image Classificationcited by 0
  4. 2025Enhancing Dual Network Based Semi-Supervised Medical Image Segmentation with Uncertainty-Guided Pseudo-Labelingcited by 0
  5. 2026Deep Modeling and Interpretation for Bladder Cancer Classificationcited by 0
  6. 2026Impact of domain adaptation in deep learning for medical image classificationscited by 0