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 titleError rate Publication date
Convolutional Deep Belief Networks on CIFAR-1021.1August, 2010
Maxout Networks9.38
Wide Residual Networks4.0
Neural Architecture Search with Reinforcement Learning3.65
Fractional Max-Pooling3.47
Densely Connected Convolutional Networks3.46
Shake-Shake regularization2.86
Coupled Ensembles of Neural Networks2.68
ShakeDrop regularization2.67Feb 7, 2018
Improved Regularization of Convolutional Neural Networks with Cutout2.56Aug 15, 2017
Regularized Evolution for Image Classifier Architecture Search2.13Feb 6, 2018
Rethinking Recurrent Neural Networks and other Improvements for Image Classification1.64July 31, 2020
AutoAugment: Learning Augmentation Policies from Data1.48May 24, 2018
A Survey on Neural Architecture Search1.33May 4, 2019
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism1.00Nov 16, 2018
Reduction of Class Activation Uncertainty with Background Information0.95May 5, 2023
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale0.52021

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.
Category:Datasets in computer vision