mlsanityData to 14 Oct 2026

Online Hyper-parameter Learning for Auto-Augmentation Strategy

arXiv 1905.07373 ↗First posted 17 May 2019cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

Data augmentation is critical to the success of modern deep learning techniques. In this paper, we propose Online Hyper-parameter Learning for Auto-Augmentation (OHL-Auto-Aug), an economical solution that learns the augmentation policy distribution along with network training. Unlike previous methods on auto-augmentation that search augmentation strategies in an offline manner, our method formulates the augmentation policy as a parameterized probability distribution, thus allowing its parameters to be optimized jointly with network parameters. Our proposed OHL-Auto-Aug eliminates the need of re-training and dramatically reduces the cost of the overall search process, while establishes significantly accuracy improvements over baseline models. On both CIFAR-10 and ImageNet, our method achieves remarkable on search accuracy, 60x faster on CIFAR-10 and 24x faster on ImageNet, while maintaining competitive accuracies.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 7; 2023: 8; 2024: 5; 2025: 1; 2026: 5.

38 papers.

Sort:

  1. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 227
  2. 2022Image Data Augmentation for Deep Learning: A Surveycited by 96
  3. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 95
  4. 2023Vision Transformer with Quadrangle Attentioncited by 46
  5. 2022VSA: Learning Varied-Size Window Attention in Vision Transformerscited by 43
  6. 2021HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networkscited by 38
  7. 2022TeachAugment: Data Augmentation Optimization Using Teacher Knowledgecited by 37
  8. 2021Direct Differentiable Augmentation Searchcited by 28
  9. 2024Swift Sampler: Efficient Learning of Sampler by 10 Parameterscited by 25
  10. 2021CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signalscited by 22
  11. 2021AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiationcited by 14
  12. 2024Automated data processing and feature engineering for deep learning and big data applications: a surveycited by 14
26 more
  1. 2021Learning Augmentation Distributions using Transformed Risk Minimizationcited by 13
  2. 2023When to Learn What: Model-Adaptive Data Augmentation Curriculumcited by 13
  3. 2022A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Taskscited by 12
  4. 2021SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentationcited by 10
  5. 2021Local Patch AutoAugment with Multi-Agent Collaborationcited by 8
  6. 2021DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecturecited by 6
  7. 2023AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentationcited by 6
  8. 2023SLACK: Stable Learning of Augmentations with Cold-start and KL regularizationcited by 6
  9. 2023Anchor Data Augmentationcited by 6
  10. 2022Universal Adaptive Data Augmentationcited by 5
  11. 2025Sample-aware RandAugment: Search-free Automatic Data Augmentation for Effective Image Recognitioncited by 5
  12. 2024FreeAugment: Data Augmentation Search Across All Degrees of Freedomcited by 3
  13. 2022Adversarial Learning of Hard Positives for Place Recognitioncited by 2
  14. 2021ParticleAugment: Sampling-Based Data Augmentationcited by 1
  15. 2021AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptationcited by 1
  16. 2023Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Imagescited by 1
  17. 2024Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methodscited by 1
  18. 2026Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videoscited by 1
  19. 2021Man versus Machine: AutoML and Human Experts' Role in Phishing Detectioncited by 0
  20. 2023Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Studycited by 0
  21. 2023Dynamic Data Augmentation via MCTS for Prostate MRI Segmentationcited by 0
  22. 2024Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusioncited by 0
  23. 2026Ctrl-A: Control-Driven Online Data Augmentationcited by 0
  24. 2026Learning Adversarial Augmentation Policies for Robust Garlic Seedling Detectioncited by 0
  25. 2026Learning-State-Aware Dynamic Generative Data Augmentation on Small-Scale Datasetscited by 0
  26. 2026Constrained Hyperparameter Optimization for Streaming Datacited by 0