mlsanityData to 14 Oct 2026

Fast AutoAugment

arXiv 1905.00397 ↗First posted 1 May 2019cs.LG cs.CV stat.MLcited by 243

Not on the map. Why?

Abstract (arXiv)

Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically search for augmentation policies from a dataset and has significantly enhanced performances on many image recognition tasks. However, its search method requires thousands of GPU hours even for a relatively small dataset. In this paper, we propose an algorithm called Fast AutoAugment that finds effective augmentation policies via a more efficient search strategy based on density matching. In comparison to AutoAugment, the proposed algorithm speeds up the search time by orders of magnitude while achieves comparable performances on image recognition tasks with various models and datasets including CIFAR-10, CIFAR-100, SVHN, and ImageNet.

Key facts. Cited by 243 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 74; 2022: 62; 2023: 50; 2024: 36; 2025: 13; 2026: 8.

243 papers.

Sort:

By area:

  1. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  2. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
  3. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  4. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  5. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 227
  6. 2021Towards Causal Representation Learningcited by 209
  7. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 193
  8. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 156
  9. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  10. 2021Contrastive Learning with Stronger Augmentationscited by 100
  11. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  12. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 97
38 more
  1. 2024DiffuseMix: Label-Preserving Data Augmentation with Diffusion Modelscited by 78
  2. 2022Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?cited by 67
  3. 2022Crafting Better Contrastive Views for Siamese Representation Learningcited by 67
  4. 2022Expanding Small-Scale Datasets with Guided Imaginationcited by 62
  5. 2022C-Mixup: Improving Generalization in Regressioncited by 57
  6. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  7. 2022Neuromorphic Data Augmentation for Training Spiking Neural Networkscited by 52
  8. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  9. 2022AutoBalance: Optimized Loss Functions for Imbalanced Datacited by 49
  10. 2021Learning Partial Equivariances from Datacited by 45
  11. 2021Contrastive Multimodal Fusion with TupleInfoNCEcited by 43
  12. 2021Robust and Accurate Object Detection via Adversarial Learningcited by 42
  13. 2024A Comprehensive Survey on Data Augmentationcited by 40
  14. 2021Point Cloud Augmentation with Weighted Local Transformationscited by 39
  15. 2022TeachAugment: Data Augmentation Optimization Using Teacher Knowledgecited by 37
  16. 2022Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspectivecited by 37
  17. 2021AutoDropout: Learning Dropout Patterns to Regularize Deep Networkscited by 35
  18. 2025MAT-Agent: Adaptive Multi-Agent Training Optimizationcited by 35
  19. 2021CrossNorm and SelfNorm for Generalization under Distribution Shiftscited by 33
  20. 2023CUDA: Curriculum of Data Augmentation for Long-Tailed Recognitioncited by 30
  21. 2021Direct Differentiable Augmentation Searchcited by 28
  22. 2022Sample Efficiency of Data Augmentation Consistency Regularizationcited by 28
  23. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  24. 2021Survey: Image Mixing and Deleting for Data Augmentationcited by 26
  25. 2023On Efficient Training of Large-Scale Deep Learning Models: A Literature Reviewcited by 26
  26. 2022AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detectioncited by 25
  27. 2021Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classificationcited by 23
  28. 2021Scale-aware Automatic Augmentation for Object Detectioncited by 23
  29. 2023Image Data Augmentation Approaches: A Comprehensive Survey and Future directionscited by 23
  30. 2024Understanding Test-Time Augmentationcited by 23
  31. 2021Learning Representational Invariances for Data-Efficient Action Recognitioncited by 22
  32. 2021CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signalscited by 22
  33. 2021Reweighting Augmented Samples by Minimizing the Maximal Expected Losscited by 21
  34. 2022Automated Data Augmentations for Graph Classificationcited by 20
  35. 2022FHIST: A Benchmark for Few-shot Classification of Histological Imagescited by 20
  36. 2023Feature Fusion from Head to Tail for Long-Tailed Visual Recognitioncited by 20
  37. 2024Uncertainty-Calibrated Test-Time Model Adaptation without Forgettingcited by 20
  38. 2023The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Modelscited by 19

50 most cited of 243 All 243 (JSON)