CoChat
Sign Up
Cited by 3,223Machine Learning and Data ClassificationAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

Randaugment: Practical automated data augmentation with a reduced search space

Open access
Cubuk, Ekin D., Zoph, Barret, Shlens, Jonathon, Le, Quoc V.·2020·2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
DOI 10.1109/cvprw50498.2020.00359
Open this paper in CoChat — free accountOpen PDF

Abstract

Recent work on automated augmentation strategies has led to state-of-the-art results in image classification and object detection. An obstacle to a large-scale adoption of these methods is that they require a separate and expensive search phase. A common way to overcome the expense of the search phase was to use a smaller proxy task. However, it was not clear if the optimized hyperparameters found on the proxy task are also optimal for the actual task. In this work, we rethink the process of designing automated augmentation strategies. We find that while previous work required a search for both magnitude and probability of each operation independently, it is sufficient to only search for a single distortion magnitude that jointly controls all operations. We hence propose a simplified search space that vastly reduces the computational expense of automated augmentation, and permits the removal of a separate proxy task. Despite the simplifications, our method achieves equal or better performance over previous automated augmentation strategies on on CIFAR-10/100, SVHN, ImageNet and COCO datasets. EfficientNet-B7, we achieve 85.0% accuracy, a 1.0% increase over baseline augmentation, a 0.6% improvement over AutoAugment on the ImageNet dataset. With EfficientNet-B8, we achieve 85.4% accuracy on ImageNet, which matches a previous result that used 3.5B extra images. On object detection, the same method as classification leads to 1.0-1.3% improvement over baseline augmentation. Code will be made available online.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvprw50498.2020.00359

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Combining augmentations through a RandAugment policy reduces the pose score by 89% on Lightbox and 93% on Sunlamp.

    “Combining these augmentations through a RandAugment [64] policy significantly reduces the pose score, i.e ., by 89% on Lightbox and 93% on Sunlamp .”

    From Domain Generalization for In-Orbit 6D Pose Estimation (2025) · cites this paper as [64]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 51

  1. Antreas Antoniou, Amos Storkey, and Harrison Edwards. Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340, 2017. 2 · arXiv
  2. Liang-Chieh Chen, Maxwell Collins, Yukun Zhu, George Papandreou, Barret Zoph, Florian Schroff, Hartwig Adam, and Jon Shlens. Searching for efficient multi-scale archi- tectures for dense image prediction. In Advances in Neural Information Processing Systems, pages 8699-8710, 2018. 2
  3. Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolu- tion, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4):834-848, 2017. 8
  4. Dan Ciregan, Ueli Meier, and Jürgen Schmidhuber. Multi- column deep neural networks for image classification. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pages 3642-3649. IEEE, 2012. 2
  5. Ekin D Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasude- van, and Quoc V Le. Autoaugment: Learning augmentation policies from data. arXiv preprint arXiv:1805.09501, 2018. 1, 2, 3, 4, 5, 6, 7, 8 · arXiv
  6. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009. 1, 2
  7. Terrance DeVries and Graham W Taylor. Dataset augmen- tation in feature space. arXiv preprint arXiv:1702.05538, 2017. 1, 2, 8 · arXiv
  8. Terrance DeVries and Graham W Taylor. Improved regular- ization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552, 2017. 2, 6 · arXiv
  9. Debidatta Dwibedi, Ishan Misra, and Martial Hebert. Cut, paste and learn: Surprisingly easy synthesis for instance de- tection. In Proceedings of the IEEE International Confer- ence on Computer Vision, pages 1301-1310, 2017. 2
  10. Hao-Shu Fang, Jianhua Sun, Runzhong Wang, Minghao Gou, Yong-Lu Li, and Cewu Lu. Instaboost: Boosting instance segmentation via probability map guided copy- pasting. arXiv preprint arXiv:1908.07801, 2019. 1 · arXiv
  11. Nic Ford, Justin Gilmer, Nicolas Carlini, and Dogus Cubuk. Adversarial examples are a natural consequence of test error in noise. arXiv preprint arXiv:1901.10513, 2019. 2 · arXiv
  12. Xavier Gastaldi. Shake-shake regularization. arXiv preprint arXiv:1705.07485, 2017. 4, 13 · arXiv
  13. Daniel Golovin, Benjamin Solnik, Subhodeep Moitra, Greg Kochanski, John Karro, and D Sculley. Google vizier: A service for black-box optimization. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1487-1495. ACM, 2017. 4
  14. Dongyoon Han, Jiwhan Kim, and Junmo Kim. Deep pyrami- dal residual networks. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 6307-6315. IEEE, 2017. 1
  15. Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, et al. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567, 2014. 1 · arXiv
  16. Shawn Hershey, Sourish Chaudhuri, Daniel PW Ellis, Jort F Gemmeke, Aren Jansen, R Channing Moore, Manoj Plakal, Devin Platt, Rif A Saurous, Bryan Seybold, et al. Cnn archi- tectures for large-scale audio classification. In 2017 ieee in- ternational conference on acoustics, speech and signal pro- cessing (icassp), pages 131-135. IEEE, 2017. 8
  17. Geoffrey Hinton, Li Deng, Dong Yu, George Dahl, Abdel- rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Brian Kingsbury, et al. Deep neural networks for acoustic modeling in speech recognition. IEEE Signal processing magazine, 29, 2012. 8
  18. Daniel Ho, Eric Liang, Ion Stoica, Pieter Abbeel, and Xi Chen. Population based augmentation: Efficient learn- ing of augmentation policy schedules. arXiv preprint arXiv:1905.05393, 2019. 1, 2, 3, 4, 7, 8 · arXiv
  19. Naoyuki Kanda, Ryu Takeda, and Yasunari Obuchi. Elastic spectral distortion for low resource speech recognition with deep neural networks. In 2013 IEEE Workshop on Auto- matic Speech Recognition and Understanding, pages 309- 314. IEEE, 2013. 1
  20. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neural net- works. In Advances in Neural Information Processing Sys- tems, 2012. 1, 2, 8
  21. Joseph Lemley, Shabab Bazrafkan, and Peter Corcoran. Smart augmentation learning an optimal data augmentation strategy. IEEE Access, 5:5858-5869, 2017. 2
  22. Sungbin Lim, Ildoo Kim, Taesup Kim, Chiheon Kim, and Sungwoong Kim. Fast autoaugment. arXiv preprint arXiv:1905.00397, 2019. 1, 2, 3, 4, 7, 8 · arXiv
  23. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740-755. Springer, 2014. 2, 6
  24. Chenxi Liu, Barret Zoph, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, and Kevin Mur- phy. Progressive neural architecture search. arXiv preprint arXiv:1712.00559, 2017. 2, 6 · arXiv
  25. Hanxiao Liu, Karen Simonyan, and Yiming Yang. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055, 2018. 2, 7, 8, 12 · arXiv
  26. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. Ssd: Single shot multibox detector. In European con- ference on computer vision, pages 21-37. Springer, 2016. 2
  27. Raphael Gontijo Lopes, Dong Yin, Ben Poole, Justin Gilmer, and Ekin D Cubuk. Improving robustness without sacrificing accuracy with patch gaussian augmentation. arXiv preprint arXiv:1906.02611, 2019. 1, 2, 6, 8 · arXiv
  28. Seongkyu Mun, Sangwook Park, David K Han, and Hanseok Ko. Generative adversarial network based acoustic scene training set augmentation and selection using svm hyper- plane. In Detection and Classification of Acoustic Scenes and Events Workshop, 2017. 2
  29. Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bis- sacco, Bo Wu, and Andrew Y Ng. Reading digits in natural images with unsupervised feature learning. In NIPS Work- shop on Deep Learning and Unsupervised Feature Learning, 2011. 1, 2, 6
  30. Jiquan Ngiam, Benjamin Caine, Wei Han, Brandon Yang, Yuning Chai, Pei Sun, Yin Zhou, Xi Yi, Ouais Al- sharif, Patrick Nguyen, et al. Starnet: Targeted compu- tation for object detection in point clouds. arXiv preprint arXiv:1908.11069, 2019. 8 · arXiv
  31. Daniel S Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D Cubuk, and Quoc V Le. Specaug- ment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779, 2019. 1, 4, 8 · arXiv
  32. Luis Perez and Jason Wang. The effectiveness of data aug- mentation in image classification using deep learning. arXiv preprint arXiv:1712.04621, 2017. 2 · arXiv
  33. Hieu Pham, Melody Y Guan, Barret Zoph, Quoc V Le, and Jeff Dean. Efficient neural architecture search via parameter sharing. In International Conference on Machine Learning, 2018. 2
  34. Alexander J Ratner, Henry Ehrenberg, Zeshan Hussain, Jared Dunnmon, and Christopher Ré. Learning to compose domain-specific transformations for data augmentation. In Advances in Neural Information Processing Systems, pages 3239-3249, 2017. 2
  35. Suman Ravuri and Oriol Vinyals. Classification accuracy score for conditional generative models. arXiv preprint arXiv:1905.10887, 2019. 2 · arXiv
  36. Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, and Vaishaal Shankar. Do imagenet classifiers generalize to im- agenet? arXiv preprint arXiv:1902.10811, 2019. 1, 8 · arXiv
  37. Ikuro Sato, Hiroki Nishimura, and Kensuke Yokoi. Apac: Augmented pattern classification with neural networks. arXiv preprint arXiv:1505.03229, 2015. 2 · arXiv
  38. Patrice Y Simard, David Steinkraus, John C Platt, et al. Best practices for convolutional neural networks applied to visual document analysis. In Proceedings of International Confer- ence on Document Analysis and Recognition, 2003. 1, 2, 8
  39. Leon Sixt, Benjamin Wild, and Tim Landgraf. Render- gan: Generating realistic labeled data. arXiv preprint arXiv:1611.01331, 2016. 2 · arXiv
  40. Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199, 2013. 2 · arXiv
  41. Toan Tran, Trung Pham, Gustavo Carneiro, Lyle Palmer, and Ian Reid. A bayesian data augmentation approach for learn- ing deep models. In Advances in Neural Information Pro- cessing Systems, pages 2794-2803, 2017. 2
  42. Li Wan, Matthew Zeiler, Sixin Zhang, Yann Le Cun, and Rob Fergus. Regularization of neural networks using drop- connect. In International Conference on Machine Learning, pages 1058-1066, 2013. 2
  43. Qizhe Xie, Zihang Dai, Eduard Hovy, Minh-Thang Luong, and Quoc V Le. Unsupervised data augmentation. arXiv preprint arXiv:1904.12848, 2019. 1, 6, 8 · arXiv
  44. Yoshihiro Yamada, Masakazu Iwamura, and Koichi Kise. Shakedrop regularization. arXiv preprint arXiv:1802.02375, 2018. 4, 13 · arXiv
  45. Dong Yin, Raphael Gontijo Lopes, Jonathon Shlens, Ekin D Cubuk, and Justin Gilmer. A fourier perspective on model robustness in computer vision. arXiv preprint arXiv:1906.08988, 2019. 1, 2, 8 · arXiv
  46. Sergey Zagoruyko and Nikos Komodakis. Wide residual net- works. In British Machine Vision Conference, 2016. 1, 2, 4, 5, 7
  47. Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. mixup: Beyond empirical risk minimiza- tion. arXiv preprint arXiv:1710.09412, 2017. 1, 2, 8 · arXiv
  48. Xinyue Zhu, Yifan Liu, Zengchang Qin, and Jiahong Li. Data augmentation in emotion classification using genera- tive adversarial networks. arXiv preprint arXiv:1711.00648, 2017. 2 · arXiv
  49. Barret Zoph, Ekin D Cubuk, Golnaz Ghiasi, Tsung-Yi Lin, Jonathon Shlens, and Quoc V Le. Learning data aug- mentation strategies for object detection. arXiv preprint arXiv:1906.11172, 2019. 1, 4, 6, 7, 8, 13 · arXiv
  50. Barret Zoph and Quoc V Le. Neural architecture search with reinforcement learning. In International Conference on Learning Representations, 2017. 2, 4
  51. Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V Le. Learning transferable architectures for scalable image recognition. In Proceedings of IEEE Conference on Com- puter Vision and Pattern Recognition, 2017. 2, 4, 6

Cited by

Sorted by citations

Authors
Cubuk, E. D., Zoph, B., Shlens, J., & Le, Q. V.
Affiliations
Google (United States) (US)
ORCID
Venue
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Publisher
IEEE
Published
2020-06
Volume
33
Pages
3008-3017
DOI
10.1109/cvprw50498.2020.00359
OpenAlex
W2993466051
Cited by
3,223
References
9
Citations by year
2026: 320 · 2025: 600 · 2024: 683 · 2023: 733 · 2022: 493 · 2021: 279 · 2020: 110 · 2019: 5
FWCI
154.24
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
  • neural information processing systems
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
search space reduction, proxy tasks, image classification, object detection, EfficientNet, computational efficiency

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review