mlsanityData to 7 Oct 2026

Domain Invariant Representation Learning with Domain Density Transformations

arXiv 2102.05082 ↗First posted 9 Feb 2021cs.LGcited by 53

Not on the map. Why?

Abstract (arXiv)

Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all source domains) has been shown to perform suboptimally, since the information learned by that model might be domain-specific and generalize imperfectly to target domains. To tackle this problem, a predominant approach is to find and learn some domain-invariant information in order to use it for the prediction task. In this paper, we propose a theoretically grounded method to learn a domain-invariant representation by enforcing the representation network to be invariant under all transformation functions among domains. We also show how to use generative adversarial networks to learn such domain transformations to implement our method in practice. We demonstrate the effectiveness of our method on several widely used datasets for the domain generalization problem, on all of which we achieve competitive results with state-of-the-art models.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 38 of its 68 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

38 of 68 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2019Invariant Risk Minimizationcited by 1,832
  6. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  7. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  8. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  9. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  10. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  11. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  12. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
26 more
  1. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  2. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  3. 2013Domain Generalization via Invariant Feature Representationcited by 622
  4. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  5. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  6. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  7. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
  8. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  9. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  10. 2016Coupled Generative Adversarial Networkscited by 216
  11. 2019Learning to Optimize Domain Specific Normalization for Domain Generalizationcited by 160
  12. 2018Domain Generalization via Conditional Invariant Representationcited by 146
  13. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  14. 2020Learning to Balance Specificity and Invariance for In and Out of Domain Generalizationcited by 128
  15. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 124
  16. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  17. 2019DIVA: Domain Invariant Variational Autoencoderscited by 114
  18. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  19. 2014Domain-Adversarial Neural Networkscited by 78
  20. 2018Domain Generalization with Domain-Specific Aggregation Modulescited by 61
  21. 2017From source to target and back: symmetric bi-directional adaptive GANcited by 53
  22. 2019Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalizationcited by 43
  23. 2019AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flowscited by 33
  24. 2020Respecting Domain Relations: Hypothesis Invariance for Domain Generalizationcited by 30
  25. 2019Alpha MAML: Adaptive Model-Agnostic Meta-Learningcited by 25
  26. 2020DIRL: Domain-Invariant Representation Learning for Sim-to-Real Transfercited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 12; 2023: 11; 2024: 10; 2025: 14; 2026: 3.

53 papers.

Sort:

By area:

  1. 2021OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalizationcited by 86
  2. 2022Less Data, More Knowledge: Building Next Generation Semantic Communication Networkscited by 61
  3. 2023A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidancecited by 40
  4. 2021KL Guided Domain Adaptationcited by 35
  5. 2024DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learningcited by 32
  6. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  7. 2023Fairness and Accuracy under Domain Generalizationcited by 24
  8. 2022The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalizationcited by 21
  9. 2022Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencodercited by 18
  10. 2022CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesionscited by 17
  11. 2024Beyond Pixels: Text Enhances Generalization in Real-World Image Restorationcited by 17
  12. 2023Energy-Based Test Sample Adaptation for Domain Generalizationcited by 14
38 more
  1. 2024Generalizing across Temporal Domains with Koopman Operatorscited by 12
  2. 2023Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environmentcited by 11
  3. 2023Moderately Distributional Exploration for Domain Generalizationcited by 8
  4. 2023Invariant Anomaly Detection under Distribution Shifts: A Causal Perspectivecited by 8
  5. 2024Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clientscited by 7
  6. 2022Generalizability of Adversarial Robustness Under Distribution Shiftscited by 6
  7. 2024Domain Adaptation with Cauchy-Schwarz Divergencecited by 6
  8. 2025Fundamental Limits of Perfect Concept Erasurecited by 5
  9. 2022FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalizationcited by 4
  10. 2022Robust Self-Supervised Learning with Lie Groupscited by 4
  11. 2024Non-stationary Domain Generalization: Theory and Algorithmcited by 3
  12. 2022Domain Decorrelation with Potential Energy Rankingcited by 2
  13. 2022Joint covariate-alignment and concept-alignment: a framework for domain generalizationcited by 2
  14. 2024Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptationcited by 2
  15. 2025Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariancecited by 2
  16. 2025Why Domain Generalization Fail? A View of Necessity and Sufficiencycited by 2
  17. 2025Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergiescited by 2
  18. 2025From Invariant Representations to Invariant Data: Provable Robustness to Spurious Correlations via Noisy Counterfactual Matchingcited by 2
  19. 2025Domain Generalization via Pareto Optimal Gradient Matchingcited by 2
  20. 2022Evolving Domain Generalizationcited by 1
  21. 2022UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation Pipelinecited by 1
  22. 2023EnfoMax: Domain Entropy and Mutual Information Maximization for Domain Generalized Face Anti-spoofingcited by 1
  23. 2023Energy-Efficient and Real-Time Sensing for Federated Continual Learning via Sample-Driven Controlcited by 1
  24. 2023Bayesian Domain Invariant Learning via Posterior Generalization of Parameter Distributionscited by 1
  25. 2024Learning Conditional Invariances through Non-Commutativitycited by 1
  26. 2025Generalized and Personalized Federated Learning with Black-Box Foundation Models via Orthogonal Transformationscited by 1
  27. 2021Beyond Low Earth Orbit: Biomonitoring, Artificial Intelligence, and Precision Space Healthcited by 0
  28. 2022Structural State Translation: Condition Transfer between Civil Structures Using Domain-Generalization for Structural Health Monitoringcited by 0
  29. 2023Domain Generalization for Domain-Linked Classescited by 0
  30. 2024PARDON: Privacy-Aware and Robust Federated Domain Generalizationcited by 0
  31. 2024Guidance Not Obstruction: A Conjugate Consistent Enhanced Strategy for Domain Generalizationcited by 0
  32. 2025Representation Convergence: Mutual Distillation is Secretly a Form of Regularizationcited by 0
  33. 2025Meta Learning not to Learn: Robustly Informing Meta-Learning under Nuisance-Varying Familiescited by 0
  34. 2025Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domainscited by 0
  35. 2025Knowledge Abstraction for Knowledge-based Semantic Communication: A Generative Causality Invariant Approachcited by 0
  36. 2025Physics-Informed Mixture Models and Surrogate Models for Precision Additive Manufacturingcited by 0
  37. 2025RobustSurg: Tackling domain generalisation for out-of-distribution surgical scene segmentationcited by 0
  38. 2025Federated Domain Generalization with Latent Space Inversioncited by 0

50 most cited of 53 All 53 (JSON)