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.

CIFAR-10 is a labeled subset of the 80 Million Tiny Images dataset from 2008, published in 2009. When the dataset was created, students were paid to label all of the images.[5]

Various kinds of convolutional neural networks tend to be the best at recognizing the images in CIFAR-10.

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.

Paper title Error rate (%) Publication date
Convolutional Deep Belief Networks on CIFAR-10[6] 21.1 August, 2010
Maxout Networks[7] 9.38 February 13, 2013
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
Densely Connected Convolutional Networks[11] 3.46 August 24, 2016
Shake-Shake regularization[12] 2.86 May 21, 2017
Coupled Ensembles of Neural Networks[13] 2.68 September 18, 2017
ShakeDrop regularization[14] 2.67 Feb 7, 2018
Improved Regularization of Convolutional Neural Networks with Cutout[15] 2.56 Aug 15, 2017
Regularized Evolution for Image Classifier Architecture Search[16] 2.13 Feb 6, 2018
Rethinking Recurrent Neural Networks and other Improvements for Image Classification[17] 1.64 July 31, 2020
AutoAugment: Learning Augmentation Policies from Data[18] 1.48 May 24, 2018
A Survey on Neural Architecture Search[19] 1.33 May 4, 2019
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism[20] 1.00 Nov 16, 2018
Reduction of Class Activation Uncertainty with Background Information[21] 0.95 May 5, 2023
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale[22] 0.5 2021

Benchmarks

edit

CIFAR-10 is also used as a performance benchmark for teams competing to run neural networks faster and cheaper. DAWNBench has benchmark data on their website.

See also

edit

References

edit
  1. ^ "AI Progress Measurement". Electronic Frontier Foundation. 2017-06-12. Retrieved 2017-12-11.
  2. ^ "Popular Datasets Over Time | Kaggle". www.kaggle.com. 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. ^ Goodfellow, Ian J.; Warde-Farley, David; Mirza, Mehdi; Courville, Aaron; Bengio, Yoshua (2013-02-13). "Maxout Networks". arXiv:1302.4389 [stat.ML].
  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. ^ Huang, Gao; Liu, Zhuang; Weinberger, Kilian Q.; van der Maaten, Laurens (2016-08-24). "Densely Connected Convolutional Networks". arXiv:1608.06993 [cs.CV].
  12. ^ Gastaldi, Xavier (2017-05-21). "Shake-Shake regularization". arXiv:1705.07485 [cs.LG].
  13. ^ Dutt, Anuvabh (2017-09-18). "Coupled Ensembles of Neural Networks". arXiv:1709.06053 [cs.CV].
  14. ^ Yamada, Yoshihiro; Iwamura, Masakazu; Kise, Koichi (2018-02-07). "Shakedrop Regularization for Deep Residual Learning". IEEE Access. 7: 186126–186136. arXiv:1802.02375. doi:10.1109/ACCESS.2019.2960566. S2CID 54445621.
  15. ^ Terrance, DeVries; W., Taylor, Graham (2017-08-15). "Improved Regularization of Convolutional Neural Networks with Cutout". arXiv:1708.04552 [cs.CV].{{cite arXiv}}: CS1 maint: multiple names: authors list (link)
  16. ^ 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].
  17. ^ Nguyen, Huu P.; Ribeiro, Bernardete (2020-07-31). "Rethinking Recurrent Neural Networks and other Improvements for Image Classification". arXiv:2007.15161 [cs.CV].
  18. ^ 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].
  19. ^ Wistuba, Martin; Rawat, Ambrish; Pedapati, Tejaswini (2019-05-04). "A Survey on Neural Architecture Search". arXiv:1905.01392 [cs.LG].
  20. ^ Huang, Yanping; Cheng, Yonglong; Chen, Dehao; Lee, HyoukJoong; Ngiam, Jiquan; Le, Quoc V.; Zhifeng, Zhifeng (2018-11-16). "GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism". arXiv:1811.06965 [cs.CV].
  21. ^ Kabir, Hussain (2023-05-05). "Reduction of Class Activation Uncertainty with Background Information". arXiv:2305.03238 [cs.CV].
  22. ^ Dosovitskiy, Alexey; Beyer, Lucas; Kolesnikov, Alexander; Weissenborn, Dirk; Zhai, Xiaohua; Unterthiner, Thomas; Dehghani, Mostafa; Minderer, Matthias; Heigold, Georg; Gelly, Sylvain; Uszkoreit, Jakob; Houlsby, Neil (2021). "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale". International Conference on Learning Representations. arXiv:2010.11929.
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.