mlsanityData to 7 Oct 2026

Variational Disentanglement for Domain Generalization

arXiv 2109.05826 ↗First posted 13 Sep 2021cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Domain generalization aims to learn an invariant model that can generalize well to the unseen target domain. In this paper, we propose to tackle the problem of domain generalization by delivering an effective framework named Variational Disentanglement Network (VDN), which is capable of disentangling the domain-specific features and task-specific features, where the task-specific features are expected to be better generalized to unseen but related test data. We further show the rationale of our proposed method by proving that our proposed framework is equivalent to minimize the evidence upper bound of the divergence between the distribution of task-specific features and its invariant ground truth derived from variational inference. We conduct extensive experiments to verify our method on three benchmarks, and both quantitative and qualitative results illustrate the effectiveness of our method.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 60 of its 85 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

60 of 85 references.

References · 60

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2019Invariant Risk Minimizationcited by 1,832
  5. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  7. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  8. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  9. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  10. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  11. 2016Deep Variational Information Bottleneckcited by 915
  12. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
38 more
  1. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  4. 2018Which Training Methods for GANs do actually Converge?cited by 672
  5. 2013Domain Generalization via Invariant Feature Representationcited by 622
  6. 2021Domain Generalization with MixStylecited by 563
  7. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  8. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  9. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  10. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  11. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  12. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  13. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  14. 2021A Fourier-based Framework for Domain Generalizationcited by 287
  15. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  16. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  17. 2019Episodic Training for Domain Generalizationcited by 245
  18. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  19. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  20. 2020Invariant Risk Minimization Gamescited by 188
  21. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  22. 2019Learning to Optimize Domain Specific Normalization for Domain Generalizationcited by 160
  23. 2020Domain Adaptive Ensemble Learningcited by 156
  24. 2017Generalization in Deep Learningcited by 146
  25. 2018Domain Generalization via Conditional Invariant Representationcited by 146
  26. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  27. 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
  28. 2020Learning to Balance Specificity and Invariance for In and Out of Domain Generalizationcited by 128
  29. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 124
  30. 2020Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularizationcited by 122
  31. 2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
  32. 2020Learning from Extrinsic and Intrinsic Supervisions for Domain Generalizationcited by 108
  33. 2019Domain Agnostic Learning with Disentangled Representationscited by 107
  34. 2020Heterogeneous Domain Generalization via Domain Mixupcited by 103
  35. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  36. 2015Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalizationcited by 96
  37. 2020Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learningcited by 93
  38. 2018Bias and Generalization in Deep Generative Models: An Empirical Studycited by 83

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 8; 2024: 0; 2025: 5.

18 papers.

Sort:

By area:

  1. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  2. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 47
  3. 2021MVDG: A Unified Multi-view Framework for Domain Generalizationcited by 20
  4. 2022Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencodercited by 18
  5. 2023Temporal Coherent Test-Time Optimization for Robust Video Classificationcited by 15
  6. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12
  7. 2023Diverse Target and Contribution Scheduling for Domain Generalizationcited by 10
  8. 2023Towards Counterfactual Fairness-aware Domain Generalization in Changing Environmentscited by 8
  9. 2021Instrumental Variable-Driven Domain Generalization with Unobserved Confounderscited by 7
  10. 2022MultiMatch: Multi-task Learning for Semi-supervised Domain Generalizationcited by 7
  11. 2025Domain Generalization via Discrete Codebook Learningcited by 3
  12. 2025Discovering Hierarchy-Grounded Domains with Adaptive Granularity for Clinical Domain Generalizationcited by 3
6 more
  1. 2023Removing Image Artifacts From Scratched Lens Protectorscited by 2
  2. 2023Towards Domain-Specific Features Disentanglement for Domain Generalizationcited by 1
  3. 2025Exploring Scale Shift in Crowd Localization under the Context of Domain Generalizationcited by 1
  4. 2025Mitigating Negative Transfer via Reducing Environmental Disagreementcited by 1
  5. 2023Maximizing Information in Domain-Invariant Representation Improves Transfer Learningcited by 0
  6. 2025Generative Classifier for Domain Generalizationcited by 0