mlsanityData to 7 Oct 2026

Learning to Generalize: Meta-Learning for Domain Generalization

arXiv 1710.03463 ↗First posted 10 Oct 2017cs.LGcited by 762

Not on the map. Why?

Abstract (arXiv)

Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. {Domain Generalization} (DG) techniques attempt to alleviate this issue by producing models which by design generalize well to novel testing domains. We propose a novel {meta-learning} method for domain generalization. Rather than designing a specific model that is robust to domain shift as in most previous DG work, we propose a model agnostic training procedure for DG. Our algorithm simulates train/test domain shift during training by synthesizing virtual testing domains within each mini-batch. The meta-optimization objective requires that steps to improve training domain performance should also improve testing domain performance. This meta-learning procedure trains models with good generalization ability to novel domains. We evaluate our method and achieve state of the art results on a recent cross-domain image classification benchmark, as well demonstrating its potential on two classic reinforcement learning tasks.

Key facts. Cited by 762 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 144; 2022: 157; 2023: 184; 2024: 129; 2025: 97; 2026: 51.

762 papers.

Sort:

By area:

  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2021Domain Generalization with MixStylecited by 563
  4. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
  5. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  6. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  7. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  8. 2021A Fourier-based Framework for Domain Generalizationcited by 287
  9. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  10. 2021Gradient Matching for Domain Generalizationcited by 258
  11. 2021SMIL: Multimodal Learning with Severely Missing Modalitycited by 243
  12. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
38 more
  1. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  2. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  3. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  4. 2021Learning to Diversify for Single Domain Generalizationcited by 170
  5. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
  6. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  7. 2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalizationcited by 144
  8. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
  9. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
  10. 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
  11. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  12. 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 122
  13. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  14. 2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
  15. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  16. 2021Model-Based Domain Generalizationcited by 103
  17. 2022Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understandingcited by 102
  18. 2023Sharpness-Aware Gradient Matching for Domain Generalizationcited by 102
  19. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 102
  20. 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
  21. 2023CLIPood: Generalizing CLIP to Out-of-Distributionscited by 96
  22. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  23. 2023CLIP the Gap: A Single Domain Generalization Approach for Object Detectioncited by 87
  24. 2021OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalizationcited by 86
  25. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  26. 2021Exploiting Domain-Specific Features to Enhance Domain Generalizationcited by 86
  27. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  28. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  29. 2022Semantic-Aware Domain Generalized Segmentationcited by 78
  30. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
  31. 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
  32. 2021Adaptive Methods for Real-World Domain Generalizationcited by 66
  33. 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
  34. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  35. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  36. 2021Meta-Learning to Compositionally Generalizecited by 62
  37. 2021Domain Generalization via Gradient Surgerycited by 60
  38. 2023PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalizationcited by 59

50 most cited of 762 All 762 (JSON)