mlsanityData to 7 Oct 2026

Domain Generalization via Model-Agnostic Learning of Semantic Features

arXiv 1910.13580 ↗First posted 29 Oct 2019cs.CVcited by 405

Not on the map. Why?

Abstract (arXiv)

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data such that it can directly generalize to target domains with unknown statistics. We adopt a model-agnostic learning paradigm with gradient-based meta-train and meta-test procedures to expose the optimization to domain shift. Further, we introduce two complementary losses which explicitly regularize the semantic structure of the feature space. Globally, we align a derived soft confusion matrix to preserve general knowledge about inter-class relationships. Locally, we promote domain-independent class-specific cohesion and separation of sample features with a metric-learning component. The effectiveness of our method is demonstrated with new state-of-the-art results on two common object recognition benchmarks. Our method also shows consistent improvement on a medical image segmentation task.

Key facts. Cited by 405 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 108; 2022: 85; 2023: 101; 2024: 53; 2025: 44; 2026: 14.

405 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. 2021A Fourier-based Framework for Domain Generalizationcited by 287
  8. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  9. 2021Gradient Matching for Domain Generalizationcited by 258
  10. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  11. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  12. 2021Learning to Diversify for Single Domain Generalizationcited by 170
38 more
  1. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
  2. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  3. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  4. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
  5. 2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
  6. 2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
  7. 2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
  8. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  9. 2021Model-Based Domain Generalizationcited by 103
  10. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 102
  11. 2023Sharpness-Aware Gradient Matching for Domain Generalizationcited by 102
  12. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  13. 2021Progressive Domain Expansion Network for Single Domain Generalizationcited by 96
  14. 2023MedViT: A Robust Vision Transformer for Generalized Medical Image Classificationcited by 89
  15. 2023CLIP the Gap: A Single Domain Generalization Approach for Object Detectioncited by 87
  16. 2021OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalizationcited by 86
  17. 2021Delving Deep into the Generalization of Vision Transformers under Distribution Shiftscited by 85
  18. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  19. 2022Semantic-Aware Domain Generalized Segmentationcited by 78
  20. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
  21. 2024Test-Time Model Adaptation with Only Forward Passescited by 74
  22. 2022GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspectivecited by 72
  23. 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
  24. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  25. 2021MixStyle Neural Networks for Domain Generalization and Adaptationcited by 64
  26. 2021Domain Generalization via Gradient Surgerycited by 60
  27. 2023PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalizationcited by 59
  28. 2021MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptationcited by 54
  29. 2021Intra-Inter Camera Similarity for Unsupervised Person Re-Identificationcited by 52
  30. 2021Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuningcited by 50
  31. 2021The Federated Tumor Segmentation (FeTS) Challengecited by 49
  32. 2022Pin the Memory: Learning to Generalize Semantic Segmentationcited by 48
  33. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 47
  34. 2021Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improvecited by 46
  35. 2021Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalizationcited by 45
  36. 2023Improved Test-Time Adaptation for Domain Generalizationcited by 45
  37. 2021Orthogonal Projection Losscited by 44
  38. 2021Semi-Supervised Domain Generalization with Stochastic StyleMatchcited by 43

50 most cited of 405 All 405 (JSON)