mlsanityData to 7 Oct 2026

Domain Generalization: A Survey

arXiv 2103.02503 ↗First posted 3 Mar 2021cs.LG cs.AI cs.CVcited by 760

Not on the map. Why?

Cited by 31 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the i.i.d.~assumption on source/target data, which is often violated in practice due to domain shift. Domain generalization (DG) aims to achieve OOD generalization by using only source data for model learning. Over the last ten years, research in DG has made great progress, leading to a broad spectrum of methodologies, e.g., those based on domain alignment, meta-learning, data augmentation, or ensemble learning, to name a few; DG has also been studied in various application areas including computer vision, speech recognition, natural language processing, medical imaging, and reinforcement learning. In this paper, for the first time a comprehensive literature review in DG is provided to summarize the developments over the past decade. Specifically, we first cover the background by formally defining DG and relating it to other relevant fields like domain adaptation and transfer learning. Then, we conduct a thorough review into existing methods and theories. Finally, we conclude this survey with insights and discussions on future research directions.

Key facts. Cited by 760 papers in the map (data through 7 Oct 2026). Builds on 196 of its 309 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

196 of 309 references.

References · 196

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  9. 2016Layer Normalizationcited by 5,579
  10. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  11. 2013Intriguing properties of neural networkscited by 5,114
  12. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
38 more
  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  2. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2016Learning without Forgettingcited by 2,465
  9. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  11. 2013Describing Textures in the Wildcited by 2,110
  12. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  13. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  14. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  15. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  16. 2019Invariant Risk Minimizationcited by 1,832
  17. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  18. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  19. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  20. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  21. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  22. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  23. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  24. 2019Natural Adversarial Examplescited by 1,401
  25. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  26. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  27. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  28. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  29. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  30. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  31. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  32. 2014How transferable are features in deep neural networks?cited by 1,216
  33. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  34. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  35. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  36. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  37. 2020In Search of Lost Domain Generalizationcited by 1,042
  38. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041

50 most cited of 196 All 196 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 45; 2022: 100; 2023: 182; 2024: 171; 2025: 156; 2026: 106.

760 papers.

Sort:

By area:

  1. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  2. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  3. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  4. 2021Domain Generalization with MixStylecited by 563
  5. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  6. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 409
  7. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  8. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  9. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  10. 2021A Survey of Human-in-the-loop for Machine Learningcited by 214
  11. 2021Trustworthy AI: From Principles to Practicescited by 206
  12. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
38 more
  1. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 183
  2. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  3. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  4. 2023What Makes Good Examples for Visual In-Context Learning?cited by 150
  5. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 145
  6. 2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalizationcited by 144
  7. 2022Neural Prompt Searchcited by 133
  8. 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 122
  9. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  10. 2025REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewardscited by 121
  11. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  12. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  13. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  14. 2021Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perceptioncited by 97
  15. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  16. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  17. 2021OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalizationcited by 86
  18. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  19. 2024Robust agents learn causal world modelscited by 81
  20. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
  21. 2023Federated Learning for Medical Image Analysis: A Surveycited by 77
  22. 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 71
  23. 2023A Closer Look at the Few-Shot Adaptation of Large Vision-Language Modelscited by 67
  24. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  25. 2022Full-Spectrum Out-of-Distribution Detectioncited by 63
  26. 2023Large Language Models for Supply Chain Optimizationcited by 61
  27. 2023Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Modelscited by 59
  28. 2023PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalizationcited by 59
  29. 2023Label-Free Liver Tumor Segmentationcited by 56
  30. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 48
  31. 2024Offline Training of Language Model Agents with Functions as Learnable Weightscited by 47
  32. 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Cloudscited by 46
  33. 2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
  34. 2022Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clusteringcited by 44
  35. 2021Semi-Supervised Domain Generalization with Stochastic StyleMatchcited by 43
  36. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 43
  37. 2023Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecturecited by 43
  38. 2021VT-CLIP: Enhancing Vision-Language Models with Visual-guided Textscited by 42

50 most cited of 760 All 760 (JSON)