mlsanityData to 14 Oct 2026

RandAugment: Practical automated data augmentation with a reduced search space

arXiv 1909.13719 ↗First posted 30 Sep 2019cs.CVcited by 2,269

Not on the map. Why?

Cited by 62 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and object detection. While these strategies were optimized for improving validation accuracy, they also led to state-of-the-art results in semi-supervised learning and improved robustness to common corruptions of images. An obstacle to a large-scale adoption of these methods is a separate search phase which increases the training complexity and may substantially increase the computational cost. Additionally, due to the separate search phase, these approaches are unable to adjust the regularization strength based on model or dataset size. Automated augmentation policies are often found by training small models on small datasets and subsequently applied to train larger models. In this work, we remove both of these obstacles. RandAugment has a significantly reduced search space which allows it to be trained on the target task with no need for a separate proxy task. Furthermore, due to the parameterization, the regularization strength may be tailored to different model and dataset sizes. RandAugment can be used uniformly across different tasks and datasets and works out of the box, matching or surpassing all previous automated augmentation approaches on CIFAR-10/100, SVHN, and ImageNet. On the ImageNet dataset we achieve 85.0% accuracy, a 0.6% increase over the previous state-of-the-art and 1.0% increase over baseline augmentation. On object detection, RandAugment leads to 1.0-1.3% improvement over baseline augmentation, and is within 0.3% mAP of AutoAugment on COCO. Finally, due to its interpretable hyperparameter, RandAugment may be used to investigate the role of data augmentation with varying model and dataset size. Code is available online.

Key facts. Cited by 2,269 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 395; 2022: 509; 2023: 498; 2024: 419; 2025: 279; 2026: 169.

2,269 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2022A ConvNet for the 2020scited by 3,579
  4. 2021ViViT: A Video Vision Transformercited by 1,620
  5. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  6. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  7. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  8. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  9. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  10. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  11. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  12. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
38 more
  1. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  2. 2021Perceiver: General Perception with Iterative Attentioncited by 1,104
  3. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  4. 2021Video Swin Transformercited by 1,091
  5. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  6. 2021Multiscale Vision Transformerscited by 897
  7. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  8. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  9. 2021Going deeper with Image Transformerscited by 764
  10. 2021Scaling Vision with Sparse Mixture of Expertscited by 747
  11. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 745
  12. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  13. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
  14. 2021Transformer in Transformercited by 633
  15. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 629
  16. 2021ImageNet-21K Pretraining for the Massescited by 613
  17. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 576
  18. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  19. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 569
  20. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  21. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  22. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 528
  23. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  24. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  25. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  26. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  27. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  28. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 429
  29. 2021VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Expertscited by 425
  30. 2022DeiT III: Revenge of the ViTcited by 419
  31. 2021Deep Long-Tailed Learning: A Surveycited by 417
  32. 2021A Survey of Data Augmentation Approaches for NLPcited by 409
  33. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  34. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 393
  35. 2023EVA-02: A Visual Representation for Neon Genesiscited by 381
  36. 2021ResNet strikes back: An improved training procedure in timmcited by 368
  37. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  38. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 360

50 most cited of 2,269 All 2,269 (JSON)