mlsanityData to 7 Oct 2026

Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules

arXiv 1905.05393 ↗First posted 14 May 2019cs.CV cs.LG stat.MLcited by 153

Not on the map. Why?

Abstract (arXiv)

A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations. Properly chosen augmentation policies can lead to significant generalization improvements; however, state-of-the-art approaches such as AutoAugment are computationally infeasible to run for the ordinary user. In this paper, we introduce a new data augmentation algorithm, Population Based Augmentation (PBA), which generates nonstationary augmentation policy schedules instead of a fixed augmentation policy. We show that PBA can match the performance of AutoAugment on CIFAR-10, CIFAR-100, and SVHN, with three orders of magnitude less overall compute. On CIFAR-10 we achieve a mean test error of 1.46%, which is a slight improvement upon the current state-of-the-art. The code for PBA is open source and is available at https://github.com/arcelien/pba.

Key facts. Cited by 153 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 47; 2022: 32; 2023: 40; 2024: 20; 2025: 8; 2026: 6.

153 papers.

Sort:

By area:

  1. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 225
  2. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 151
  3. 2021Contrastive Learning with Stronger Augmentationscited by 100
  4. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  5. 2022Image Data Augmentation for Deep Learning: A Surveycited by 96
  6. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
  7. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  8. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  9. 2022AutoBalance: Optimized Loss Functions for Imbalanced Datacited by 49
  10. 2023SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentationcited by 39
  11. 2024A Comprehensive Survey on Data Augmentationcited by 38
  12. 2022TeachAugment: Data Augmentation Optimization Using Teacher Knowledgecited by 37
38 more
  1. 2021Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learningcited by 35
  2. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  3. 2021Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classificationcited by 35
  4. 2021CrossNorm and SelfNorm for Generalization under Distribution Shiftscited by 33
  5. 2021Consistency-based Active Learning for Object Detectioncited by 32
  6. 2022On Implicit Bias in Overparameterized Bilevel Optimizationcited by 30
  7. 2021Direct Differentiable Augmentation Searchcited by 28
  8. 2023On Efficient Training of Large-Scale Deep Learning Models: A Literature Reviewcited by 26
  9. 2021Scale-aware Automatic Augmentation for Object Detectioncited by 23
  10. 2021CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signalscited by 22
  11. 2021Last Layer Marginal Likelihood for Invariance Learningcited by 21
  12. 2023Feature Fusion from Head to Tail for Long-Tailed Visual Recognitioncited by 20
  13. 2022Automated Data Augmentations for Graph Classificationcited by 19
  14. 2023Domain Generalization via Balancing Training Difficulty and Model Capabilitycited by 19
  15. 2023Scalarization for Multi-Task and Multi-Domain Learning at Scalecited by 19
  16. 2022Deep AutoAugmentcited by 18
  17. 2022Automatic Data Augmentation via Invariance-Constrained Learningcited by 17
  18. 2022Learning Multimodal Data Augmentation in Feature Spacecited by 17
  19. 2023Data Scarcity in Recommendation Systems: A Surveycited by 17
  20. 2022Bootstrap Generalization Ability from Loss Landscape Perspectivecited by 16
  21. 2021DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximizationcited by 15
  22. 2021Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigationcited by 15
  23. 2021Text AutoAugment: Learning Compositional Augmentation Policy for Text Classificationcited by 15
  24. 2022Learning Instance-Specific Augmentations by Capturing Local Invariancescited by 15
  25. 2021AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiationcited by 14
  26. 2021An overview of mixing augmentation methods and augmentation strategiescited by 14
  27. 2024Automated data processing and feature engineering for deep learning and big data applications: a surveycited by 14
  28. 2021Mixup Without Hesitationcited by 13
  29. 2023When to Learn What: Model-Adaptive Data Augmentation Curriculumcited by 13
  30. 2021Searching for Alignment in Face Recognitioncited by 12
  31. 2022A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Taskscited by 12
  32. 2023Understanding the Detrimental Class-level Effects of Data Augmentationcited by 12
  33. 2024Parametric Augmentation for Time Series Contrastive Learningcited by 12
  34. 2022Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentationcited by 11
  35. 2023Adaptive Training Distributions with Scalable Online Bilevel Optimizationcited by 11
  36. 2021SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentationcited by 10
  37. 2021Adaptive Weighting Scheme for Automatic Time-Series Data Augmentationcited by 8
  38. 2021Local Patch AutoAugment with Multi-Agent Collaborationcited by 8

50 most cited of 153 All 153 (JSON)