mlsanityData to 7 Oct 2026

Data Augmentation Generative Adversarial Networks

arXiv 1711.04340 ↗First posted 12 Nov 2017stat.ML cs.CV cs.LGcited by 278

Not on the map. Why?

Cited by 30 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given there is potential to generate a much broader set of augmentations, we design and train a generative model to do data augmentation. The model, based on image conditional Generative Adversarial Networks, takes data from a source domain and learns to take any data item and generalise it to generate other within-class data items. As this generative process does not depend on the classes themselves, it can be applied to novel unseen classes of data. We show that a Data Augmentation Generative Adversarial Network (DAGAN) augments standard vanilla classifiers well. We also show a DAGAN can enhance few-shot learning systems such as Matching Networks. We demonstrate these approaches on Omniglot, on EMNIST having learnt the DAGAN on Omniglot, and VGG-Face data. In our experiments we can see over 13% increase in accuracy in the low-data regime experiments in Omniglot (from 69% to 82%), EMNIST (73.9% to 76%) and VGG-Face (4.5% to 12%); in Matching Networks for Omniglot we observe an increase of 0.5% (from 96.9% to 97.4%) and an increase of 1.8% in EMNIST (from 59.5% to 61.3%).

Key facts. Cited by 278 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 70; 2022: 60; 2023: 67; 2024: 47; 2025: 22; 2026: 12.

278 papers.

Sort:

By area:

  1. 2023Effective Data Augmentation With Diffusion Modelscited by 282
  2. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  3. 2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuningcited by 150
  4. 2021Contrastive Learning with Stronger Augmentationscited by 100
  5. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  6. 2023On the Stability of Iterative Retraining of Generative Models on their own Datacited by 98
  7. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
  8. 2023Diffusion Model as Representation Learnercited by 95
  9. 2023Leaving Reality to Imagination: Robust Classification via Generated Datasetscited by 91
  10. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  11. 2022Synthesizing Informative Training Samples with GANcited by 77
  12. 2023Synthcity: facilitating innovative use cases of synthetic data in different data modalitiescited by 76
38 more
  1. 2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
  2. 2023FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Modelscited by 61
  3. 2022Will Large-scale Generative Models Corrupt Future Datasets?cited by 59
  4. 2022C-Mixup: Improving Generalization in Regressioncited by 57
  5. 2021Local Augmentation for Graph Neural Networkscited by 52
  6. 2023Training on Thin Air: Improve Image Classification with Generated Datacited by 50
  7. 2022A Closer Look at Few-shot Image Generationcited by 49
  8. 2023Synthetic Datasets for Autonomous Driving: A Surveycited by 48
  9. 2021Negative Data Augmentationcited by 46
  10. 2023Generative Adversarial Symmetry Discoverycited by 40
  11. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  12. 2022Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofingcited by 38
  13. 2022Visual Localization via Few-Shot Scene Region Classificationcited by 36
  14. 2021Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classificationcited by 35
  15. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  16. 2024Enhance Image Classification via Inter-Class Image Mixup with Diffusion Modelcited by 34
  17. 2021Featurized Density Ratio Estimationcited by 33
  18. 2022Simple and Effective Synthesis of Indoor 3D Scenescited by 33
  19. 2023Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Datacited by 31
  20. 2024A Survey on Data Augmentation in Large Model Eracited by 31
  21. 2024WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detectioncited by 31
  22. 2023Generate Your Own Scotland: Satellite Image Generation Conditioned on Mapscited by 30
  23. 2023Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Datacited by 29
  24. 2023Synthetic data, real errors: how (not) to publish and use synthetic datacited by 29
  25. 2024Towards Theoretical Understandings of Self-Consuming Generative Modelscited by 28
  26. 2021Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencodercited by 27
  27. 2021OCT-GAN: Neural ODE-based Conditional Tabular GANscited by 27
  28. 2021Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspectivecited by 25
  29. 2021Grounding inductive biases in natural images:invariance stems from variations in datacited by 25
  30. 2021Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognitioncited by 24
  31. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  32. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 23
  33. 2023Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmarkcited by 23
  34. 2021Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learningcited by 22
  35. 2022WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generationcited by 22
  36. 2022The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generationcited by 22
  37. 2022Mitigating Data Heterogeneity in Federated Learning with Data Augmentationcited by 21
  38. 2022FHIST: A Benchmark for Few-shot Classification of Histological Imagescited by 20

50 most cited of 278 All 278 (JSON)