mlsanityData to 7 Oct 2026

In Search of Lost Domain Generalization

arXiv 2007.01434 ↗First posted 2 Jul 2020cs.LG stat.MLcited by 1,042

Not on the map. Why?

Cited by 33 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The goal of domain generalization algorithms is to predict well on distributions different from those seen during training. While a myriad of domain generalization algorithms exist, inconsistencies in experimental conditions -- datasets, architectures, and model selection criteria -- render fair and realistic comparisons difficult. In this paper, we are interested in understanding how useful domain generalization algorithms are in realistic settings. As a first step, we realize that model selection is non-trivial for domain generalization tasks. Contrary to prior work, we argue that domain generalization algorithms without a model selection strategy should be regarded as incomplete. Next, we implement DomainBed, a testbed for domain generalization including seven multi-domain datasets, nine baseline algorithms, and three model selection criteria. We conduct extensive experiments using DomainBed and find that, when carefully implemented, empirical risk minimization shows state-of-the-art performance across all datasets. Looking forward, we hope that the release of DomainBed, along with contributions from fellow researchers, will streamline reproducible and rigorous research in domain generalization.

Key facts. Cited by 1,042 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 116; 2022: 217; 2023: 236; 2024: 200; 2025: 141; 2026: 132.

1,042 papers.

Sort:

By area:

  1. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  2. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  3. 2021Domain Generalization: A Surveycited by 760
  4. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
  5. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  6. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  7. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  8. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  9. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 349
  10. 2021True Few-Shot Learning with Language Modelscited by 343
  11. 2022Visual Classification via Description from Large Language Modelscited by 331
  12. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
38 more
  1. 2021Gradient Matching for Domain Generalizationcited by 258
  2. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  3. 2022Transformers in Medical Imaging: A Surveycited by 245
  4. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  5. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  6. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  7. 2022Parameter-free Online Test-time Adaptationcited by 184
  8. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  9. 2021Simple data balancing achieves competitive worst-group-accuracycited by 177
  10. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  11. 2023Large Language Model Routing with Benchmark Datasetscited by 166
  12. 2022Diverse Weight Averaging for Out-of-Distribution Generalizationcited by 148
  13. 2024WARM: On the Benefits of Weight Averaged Reward Modelscited by 145
  14. 2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalizationcited by 144
  15. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  16. 2022ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Modelscited by 141
  17. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
  18. 2021On Calibration and Out-of-domain Generalizationcited by 134
  19. 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
  20. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  21. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  22. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  23. 2023Change is Hard: A Closer Look at Subpopulation Shiftcited by 119
  24. 2021Does Invariant Risk Minimization Capture Invariance?cited by 116
  25. 2021Predicting with Confidence on Unseen Distributionscited by 116
  26. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  27. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  28. 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
  29. 2021Model-Based Domain Generalizationcited by 103
  30. 2023Sharpness-Aware Gradient Matching for Domain Generalizationcited by 102
  31. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  32. 2022Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIPcited by 97
  33. 2022Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalizationcited by 97
  34. 2023CLIPood: Generalizing CLIP to Out-of-Distributionscited by 96
  35. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  36. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  37. 2024RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Modelcited by 91
  38. 2023Generative models improve fairness of medical classifiers under distribution shiftscited by 90

50 most cited of 1,042 All 1,042 (JSON)