mlsanityData to 14 Oct 2026

Return of Frustratingly Easy Domain Adaptation

arXiv 1511.05547 ↗First posted 17 Nov 2015cs.CV cs.AI cs.LGcited by 391

Not on the map. Why?

Abstract (arXiv)

Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning methods. Supervised domain adaptation methods have been proposed for the case when the target data have labels, including some that perform very well despite being "frustratingly easy" to implement. However, in practice, the target domain is often unlabeled, requiring unsupervised adaptation. We propose a simple, effective, and efficient method for unsupervised domain adaptation called CORrelation ALignment (CORAL). CORAL minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels. Even though it is extraordinarily simple--it can be implemented in four lines of Matlab code--CORAL performs remarkably well in extensive evaluations on standard benchmark datasets.

Key facts. Cited by 391 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 105; 2022: 90; 2023: 62; 2024: 56; 2025: 48; 2026: 30.

391 papers.

Sort:

By area:

  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  2. 2021Towards Personalized Federated Learningcited by 464
  3. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  4. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 352
  5. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 294
  6. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  7. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 178
  8. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 177
  9. 2021Generalized Source-free Domain Adaptationcited by 175
  10. 2021Delving into Deep Imbalanced Regressioncited by 158
  11. 2022Diverse Weight Averaging for Out-of-Distribution Generalizationcited by 148
  12. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
38 more
  1. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  2. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  3. 2022Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalizationcited by 97
  4. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 94
  5. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  6. 2023UniverSeg: Universal Medical Image Segmentationcited by 91
  7. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  8. 2021Extending the WILDS Benchmark for Unsupervised Adaptationcited by 86
  9. 2021Unsupervised Multi-source Domain Adaptation Without Access to Source Datacited by 76
  10. 2021Cross-domain Contrastive Learning for Unsupervised Domain Adaptationcited by 76
  11. 2022Agree to Disagree: Diversity through Disagreement for Better Transferabilitycited by 70
  12. 2021VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptationcited by 69
  13. 2023PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalizationcited by 59
  14. 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
  15. 2022Unsupervised Domain Adaptation for Nighttime Aerial Trackingcited by 56
  16. 2021MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptationcited by 54
  17. 2021AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarizationcited by 51
  18. 2021DINE: Domain Adaptation from Single and Multiple Black-box Predictorscited by 51
  19. 2021Style Normalization and Restitution for Domain Generalization and Adaptationcited by 46
  20. 2021Online Adaptation to Label Distribution Shiftcited by 44
  21. 2021Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Densitycited by 44
  22. 2023Prompt-based Distribution Alignment for Unsupervised Domain Adaptationcited by 44
  23. 2022A Survey on Heterogeneous Federated Learningcited by 42
  24. 2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
  25. 2022SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloudcited by 37
  26. 2023Subspace Identification for Multi-Source Domain Adaptationcited by 37
  27. 2021One-Class Classification: A Surveycited by 35
  28. 2021Domain Generalization via Inference-time Label-Preserving Target Projectionscited by 35
  29. 2021ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptationcited by 33
  30. 2021A Survey of Unsupervised Domain Adaptation for Visual Recognitioncited by 31
  31. 2022High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learningcited by 31
  32. 2021Transformer-Based Source-Free Domain Adaptationcited by 30
  33. 2021Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environmentscited by 30
  34. 2023RLSbench: Domain Adaptation Under Relaxed Label Shiftcited by 30
  35. 2021Self-supervised Autoregressive Domain Adaptation for Time Series Datacited by 29
  36. 2022Domain Generalization using Pretrained Models without Fine-tuningcited by 29
  37. 2021Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentationcited by 28
  38. 2021Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptationcited by 28

50 most cited of 391 All 391 (JSON)