mlsanityData to 14 Oct 2026

Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve

arXiv 2102.03924 ↗First posted 7 Feb 2021cs.LG cs.CVcited by 46

Not on the map. Why?

Abstract (arXiv)

Theoretically, domain adaptation is a well-researched problem. Further, this theory has been well-used in practice. In particular, we note the bound on target error given by Ben-David et al. (2010) and the well-known domain-aligning algorithm based on this work using Domain Adversarial Neural Networks (DANN) presented by Ganin and Lempitsky (2015). Recently, multiple variants of DANN have been proposed for the related problem of domain generalization, but without much discussion of the original motivating bound. In this paper, we investigate the validity of DANN in domain generalization from this perspective. We investigate conditions under which application of DANN makes sense and further consider DANN as a dynamic process during training. Our investigation suggests that the application of DANN to domain generalization may not be as straightforward as it seems. To address this, we design an algorithmic extension to DANN in the domain generalization case. Our experimentation validates both theory and algorithm.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). Builds on 33 of its 64 references that are in the map. First posted on arXiv 7 Feb 2021.

Builds on

33 of 64 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  5. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  6. 2020In Search of Lost Domain Generalizationcited by 1,054
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  8. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  9. 2013Domain Generalization via Invariant Feature Representationcited by 623
  10. 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 533
  11. 2015Optimal Transport for Domain Adaptationcited by 463
  12. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
21 more
  1. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  2. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 407
  3. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 366
  4. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  5. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  6. 2017Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networkscited by 311
  7. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  8. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  9. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  10. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  11. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  12. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 125
  13. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  14. 2020Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularizationcited by 123
  15. 2016Theoretical Analysis of Domain Adaptation with Optimal Transportcited by 105
  16. 2019Support and Invertibility in Domain-Invariant Representationscited by 87
  17. 2020Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practicecited by 43
  18. 2020Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representationscited by 26
  19. 2018Unsupervised Domain Adaptation Based on Source-guided Discrepancycited by 20
  20. 2019Multi-Domain Adversarial Learningcited by 19
  21. 2017PAC-Bayes and Domain Adaptationcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 7; 2023: 8; 2024: 7; 2025: 7; 2026: 10.

46 papers.

Sort:

By area:

  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  2. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  3. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  4. 2023SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalizationcited by 48
  5. 2024GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusioncited by 35
  6. 2022Out-of-Distribution Representation Learning for Time Series Classificationcited by 31
  7. 2022Attention Diversification for Domain Generalizationcited by 29
  8. 2022Test-time Fourier Style Calibration for Domain Generalizationcited by 25
  9. 2022Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classificationcited by 25
  10. 2023Fairness and Accuracy under Domain Generalizationcited by 24
  11. 2023DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalizationcited by 24
  12. 2022Localized Adversarial Domain Generalizationcited by 19
34 more
  1. 2021On the benefits of representation regularization in invariance based domain generalizationcited by 17
  2. 2021On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sourcescited by 15
  3. 2021Learning Domain Invariant Representations in Goal-conditioned Block MDPscited by 12
  4. 2023EEGMatch: Learning with Incomplete Labels for Semi-Supervised EEG-based Cross-Subject Emotion Recognitioncited by 10
  5. 2023Semi-Supervised Dual-Stream Self-Attentive Adversarial Graph Contrastive Learning for Cross-Subject EEG-based Emotion Recognitioncited by 10
  6. 2024A Survey on Domain Generalization for Medical Image Analysiscited by 9
  7. 2021Robust White Matter Hyperintensity Segmentation on Unseen Domaincited by 8
  8. 2023MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learningcited by 8
  9. 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detectioncited by 7
  10. 2021Learning Domain Invariant Representations by Joint Wasserstein Distance Minimizationcited by 6
  11. 2022Towards Optimization and Model Selection for Domain Generalization: A Mixup-guided Solutioncited by 6
  12. 2022FIXED: Frustratingly Easy Domain Generalization with Mixupcited by 6
  13. 2024Enhancing Test Time Adaptation with Few-shot Guidancecited by 5
  14. 2025Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalizationcited by 5
  15. 2024InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Modelscited by 4
  16. 2026AULLM++: Structured-Token-Conditioned Large Language Models for Micro-Expression Action Unit Detectioncited by 4
  17. 2025Domain Generalization via Pareto Optimal Gradient Matchingcited by 2
  18. 2023Parameter Exchange for Robust Dynamic Domain Generalizationcited by 1
  19. 2026Beyond Physical Labels: Redefining Domains for Robust WiFi-based Gesture Recognitioncited by 1
  20. 2026Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignmentcited by 1
  21. 2026MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-Trainingcited by 1
  22. 2024M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Schedulingcited by 0
  23. 2024Guidance Not Obstruction: A Conjugate Consistent Enhanced Strategy for Domain Generalizationcited by 0
  24. 2025Fourier Asymmetric Attention on Domain Generalization for Pan-Cancer Drug Response Predictioncited by 0
  25. 2025UniBERT: Adversarial Training for Language-Universal Representationscited by 0
  26. 2025Adaptive Deep Learning for Breast Cancer Subtype Prediction Via Misprediction Risk Analysiscited by 0
  27. 2025CoDoL: Conditional Domain Prompt Learning for Out-of-Distribution Generalizationcited by 0
  28. 2025ArcGen: Generalizing Neural Backdoor Detection Across Diverse Architecturescited by 0
  29. 2026Domain Generalization for Time Series: Enhancing Drilling Regression Models for Stick-Slip Index Predictioncited by 0
  30. 2026Asymmetric Adaptation-based Real-time Fault Diagnosis Under Transitional Operating Conditionscited by 0
  31. 2026Domain-Shift Aware Neural Networks for Unbalance Characterization in Rotating Systemscited by 0
  32. 2026Temporal-Spectral Alignment with Frequency Adaptation for Source-Free Time-Series Adaptationcited by 0
  33. 2026Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarioscited by 0
  34. 2026Unified CT and MRI Pancreas Segmentation for Label-Efficient Cross-Modality Subregion Transfercited by 0