mlsanityData to 7 Oct 2026

Adversarial Bayesian Augmentation for Single-Source Domain Generalization

arXiv 2307.09520 ↗First posted 18 Jul 2023cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Generalizing to unseen image domains is a challenging problem primarily due to the lack of diverse training data, inaccessible target data, and the large domain shift that may exist in many real-world settings. As such data augmentation is a critical component of domain generalization methods that seek to address this problem. We present Adversarial Bayesian Augmentation (ABA), a novel algorithm that learns to generate image augmentations in the challenging single-source domain generalization setting. ABA draws on the strengths of adversarial learning and Bayesian neural networks to guide the generation of diverse data augmentations -- these synthesized image domains aid the classifier in generalizing to unseen domains. We demonstrate the strength of ABA on several types of domain shift including style shift, subpopulation shift, and shift in the medical imaging setting. ABA outperforms all previous state-of-the-art methods, including pre-specified augmentations, pixel-based and convolutional-based augmentations.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 42 of its 60 references that are in the map. First posted on arXiv 18 Jul 2023.

Builds on

42 of 60 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  10. 2015Spatial Transformer Networkscited by 1,423
  11. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  12. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
30 more
  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  2. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  3. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  4. 2013Domain Generalization via Invariant Feature Representationcited by 622
  5. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  6. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  7. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  8. 2020Learning to Learn Single Domain Generalizationcited by 295
  9. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  10. 2015The Variational Fair Autoencodercited by 223
  11. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  12. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  13. 2020BREEDS: Benchmarks for Subpopulation Shiftcited by 155
  14. 2020Robust and Generalizable Visual Representation Learning via Random Convolutionscited by 141
  15. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  16. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  17. 2021AugMax: Adversarial Composition of Random Augmentations for Robust Trainingcited by 89
  18. 2018Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Networkcited by 68
  19. 2018Domain Generalization with Domain-Specific Aggregation Modulescited by 61
  20. 2019Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detectioncited by 35
  21. 2017Bayesian GANcited by 31
  22. 2019Situational Fusion of Visual Representation for Visual Navigationcited by 28
  23. 2021A Bit More Bayesian: Domain-Invariant Learning with Uncertaintycited by 27
  24. 2020Attribute-Guided Adversarial Training for Robustness to Natural Perturbationscited by 23
  25. 2022Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustnesscited by 23
  26. 2022Explicit Tradeoffs between Adversarial and Natural Distributional Robustnesscited by 20
  27. 2022Improving Diversity with Adversarially Learned Transformations for Domain Generalizationcited by 16
  28. 2021Semi-supervised Models are Strong Unsupervised Domain Adaptation Learnerscited by 13
  29. 2021Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attackscited by 5
  30. 2022Fairness Increases Adversarial Vulnerabilitycited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 6; 2026: 8.

21 papers.

Sort:

  1. 2023Domain Generalization for Medical Image Analysis: A Reviewcited by 47
  2. 2024Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Samplingcited by 6
  3. 2024Towards Combating Frequency Simplicity-biased Learning for Domain Generalizationcited by 6
  4. 2024StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalizationcited by 5
  5. 2024Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalizationcited by 4
  6. 2023A Novel Cross-Perturbation for Single Domain Generalizationcited by 3
  7. 2024TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correctioncited by 2
  8. 2025Variational Learning of Disentangled Representationscited by 1
  9. 2025Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimizationcited by 1
  10. 2025ODOV: Benchmark the Open-Domain Open-Vocabulary Object Detectioncited by 1
  11. 2025Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimationcited by 1
  12. 2026Higher-Order Domain Generalization in Magnetic Resonance-Based Assessment of Alzheimer's Diseasecited by 1
9 more
  1. 2026Spectral Property-Driven Data Augmentation for Hyperspectral Single-Source Domain Generalizationcited by 1
  2. 2026RT-SDGOD: Real-Time Single-Domain Generalized Object Detectioncited by 1
  3. 2025Casual Inference via Style Bias Deconfounding for Domain Generalizationcited by 0
  4. 2025PEdger++: Practical Edge Detection via Assembling Cross Informationcited by 0
  5. 2026Beyond Seen Bounds: Class-Centric Polarization for Single-Domain Generalized Deep Metric Learningcited by 0
  6. 2026Adversarial Batch Representation Augmentation for Batch Correction in High-Content Cellular Screeningcited by 0
  7. 2026FGML-DG: Feynman-Inspired Cognitive Science Paradigm for Cross-Domain Medical Image Segmentationcited by 0
  8. 2026VFM4SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detectioncited by 0
  9. 2026ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectificationcited by 0