CIFAR-10
The CIFAR-10 dataset 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. The CIFAR-10 dataset contains 60,000 32x32 color images in 10 different classes. The 10 different classes represent airplanes, cars, birds, cats, deer, dogs, frogs, horses, ships, and trucks. There are 6,000 images of each class.
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, 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.
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
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 | 21.1 | August, 2010 |
| Maxout Networks | 9.38 | |
| Wide Residual Networks | 4.0 | |
| Neural Architecture Search with Reinforcement Learning | 3.65 | |
| Fractional Max-Pooling | 3.47 | |
| Densely Connected Convolutional Networks | 3.46 | |
| Shake-Shake regularization | 2.86 | |
| Coupled Ensembles of Neural Networks | 2.68 | |
| ShakeDrop regularization | 2.67 | Feb 7, 2018 |
| Improved Regularization of Convolutional Neural Networks with Cutout | 2.56 | Aug 15, 2017 |
| Regularized Evolution for Image Classifier Architecture Search | 2.13 | Feb 6, 2018 |
| Rethinking Recurrent Neural Networks and other Improvements for Image Classification | 1.64 | July 31, 2020 |
| AutoAugment: Learning Augmentation Policies from Data | 1.48 | May 24, 2018 |
| A Survey on Neural Architecture Search | 1.33 | May 4, 2019 |
| GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism | 1.00 | Nov 16, 2018 |
| Reduction of Class Activation Uncertainty with Background Information | 0.95 | May 5, 2023 |
| An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | 0.5 | 2021 |
Benchmarks
CIFAR-10 is also used as a performance benchmark for teams competing to run neural networks faster and cheaper. has benchmark data on their website.Similar datasets
- : Similar to CIFAR-10 but with 100 classes and 600 images each.
- : CIFAR-10 labelled with human perceptual uncertainty.
- ImageNet : 1 million color images of 1000 classes. Imagenet images are higher resolution, averaging 469x387 resolution.
- : Approximately 600,000 images of 10 classes. Also 32x32 color images.
- : CIFAR-10 is a labeled subset of this dataset.