From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

The CIFAR-10 dataset (Canadian Institute For Advanced Research) is a collection of images that are commonly used to train machine learning and computer vision algorithms. It is one of the most widely used datasets for machine learning research.[1][2] The CIFAR-10 dataset contains 60,000 32x32 color images in 10 different classes.[3] The 10 different classes represent airplanes, cars, birds, cats, deer, dogs, frogs, horses, ships, and trucks. There are 6,000 images of each class.[4]

Computer algorithms for recognizing objects in photos often learn by example. CIFAR-10 is a set of images that can be used to teach a computer how to recognize objects. Since the images in CIFAR-10 are low-resolution (32x32), this dataset can allow researchers to quickly try different algorithms to see what works. Various kinds of convolutional neural networks tend to be the best at recognizing the images in CIFAR-10.

CIFAR-10 is a labeled subset of the 80 million tiny images dataset. When the dataset was created, students were paid to label all of the images.[5]

Research Papers Claiming State-of-the-Art Results on CIFAR-10[edit]

This is a table of some of the research papers that claim to have achieved state-of-the-art results on the CIFAR-10 dataset. Not all papers are standardized on the same pre-processing techniques, like image flipping or image shifting. For that reason, it is possible that one paper's claim of state-of-the-art could have a higher error rate than an older state-of-the-art claim but still be valid.

Research Paper Error rate (%) Published Date
Convolutional Deep Belief Networks on CIFAR-10[6] 21.1 August, 2010
Densely Connected Convolutional Networks[7] 5.19 August 24, 2016
Wide Residual Networks[8] 4.0 May 23, 2016
Neural Architecture Search with Reinforcement Learning[9] 3.65 November 4, 2016
Fractional Max-Pooling[10] 3.47 December 18, 2014
Shake-Shake regularization[11] 2.86 May 21, 2017
Improved Regularization of Convolutional Neural Networks with Cutout[12] 2.56 Aug 15, 2017
ShakeDrop regularization[13] 2.31 Feb 7, 2018
Regularized Evolution for Image Classifier Architecture Search[14] 2.13 Feb 6, 2018
AutoAugment: Learning Augmentation Policies from Data[15] 1.48 May 24, 2018

See also[edit]


  1. ^ "AI Progress Measurement". Electronic Frontier Foundation. 2017-06-12. Retrieved 2017-12-11.
  2. ^ "Popular Datasets Over Time | Kaggle". Retrieved 2017-12-11.
  3. ^ Hope, Tom; Resheff, Yehezkel S.; Lieder, Itay (2017-08-09). Learning TensorFlow: A Guide to Building Deep Learning Systems. "O'Reilly Media, Inc.". pp. 64–. ISBN 9781491978481. Retrieved 22 January 2018.
  4. ^ Angelov, Plamen; Gegov, Alexander; Jayne, Chrisina; Shen, Qiang (2016-09-06). Advances in Computational Intelligence Systems: Contributions Presented at the 16th UK Workshop on Computational Intelligence, September 7–9, 2016, Lancaster, UK. Springer International Publishing. pp. 441–. ISBN 9783319465623. Retrieved 22 January 2018.
  5. ^ Krizhevsky, Alex (2009). "Learning Multiple Layers of Features from Tiny Images" (PDF).
  6. ^ "Convolutional Deep Belief Networks on CIFAR-10" (PDF).
  7. ^ Huang, Gao; Liu, Zhuang; Weinberger, Kilian Q.; van der Maaten, Laurens (2016-08-24). "Densely Connected Convolutional Networks". arXiv:1608.06993 [cs.CV].
  8. ^ Zagoruyko, Sergey; Komodakis, Nikos (2016-05-23). "Wide Residual Networks". arXiv:1605.07146 [cs.CV].
  9. ^ Zoph, Barret; Le, Quoc V. (2016-11-04). "Neural Architecture Search with Reinforcement Learning". arXiv:1611.01578 [cs.LG].
  10. ^ Graham, Benjamin (2014-12-18). "Fractional Max-Pooling". arXiv:1412.6071 [cs.CV].
  11. ^ Gastaldi, Xavier (2017-05-21). "Shake-Shake regularization". arXiv:1705.07485 [cs.LG].
  12. ^ Terrance, DeVries,; W., Taylor, Graham (2017-08-15). "Improved Regularization of Convolutional Neural Networks with Cutout". arXiv:1708.04552 [cs.CV].
  13. ^ Yamada, Yoshihiro; Iwamura, Masakazu; Kise, Koichi (2018-02-07). "ShakeDrop regularization". arXiv:1802.02375 [cs.CV].
  14. ^ Real, Esteban; Aggarwal, Alok; Huang, Yanping; Le, Quoc V. (2018-02-05). "Regularized Evolution for Image Classifier Architecture Search with Cutout". arXiv:1802.01548 [cs.NE].
  15. ^ Cubuk, Ekin D.; Zoph, Barret; Mane, Dandelion; Vasudevan, Vijay; Le, Quoc V. (2018-05-24). "AutoAugment: Learning Augmentation Policies from Data". arXiv:1805.09501 [cs.CV].

External links[edit]

Similar datasets[edit]

  • CIFAR-100: Similar to CIFAR-10 but with 100 classes and 600 images each.
  • ImageNet (ILSVRC): 1 million color images of 1000 classes. Imagenet images are higher resolution, averaging 469x387 resolution.
  • Street View House Numbers (SVHN): Approximately 600,000 images of 10 classes (digits 0-9). Also 32x32 color images.
  • 80 million tiny images dataset: CIFAR-10 is a labeled subset of this dataset.