The CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The images are labelled with one of 10 mutually exclusive classes: airplane, automobile (but not truck or pickup truck), bird, cat, deer, dog, frog, horse, ship, and truck (but not pickup truck). There are 6000 images per class with 5000 training and 1000 testing images per class.

The criteria for deciding whether an image belongs to a class were as follows:

The class name should be high on the list of likely answers to the question “What is in this picture?”
The image should be photo-realistic. Labelers were instructed to reject line drawings.
The image should contain only one prominent instance of the object to which the class refers. The object may be partially occluded or seen from an unusual viewpoint as long as its identity is still clear to the labeler.

Source: https://www.cs.toronto.edu/~kriz/cifar.html

Homepage

Benchmarks

Add a new result Link an existing benchmark

TASK	DATASET VARIANT	BEST MODEL
Image Classification	CIFAR-10	EffNet-L2
Image Generation	CIFAR-10	NCSN++ cont.
Semi-Supervised Image Classification	CIFAR-10, 4000 Labels	Meta Pseudo Labels
Conditional Image Generation	CIFAR-10	MIX-MHingeGAN
Neural Architecture Search	CIFAR-10	SharpSepConvDARTS
Neural Architecture Search	CIFAR-10 Image Classification	NAT-M4
Image Clustering	CIFAR-10	RUC
Semi-Supervised Image Classification	CIFAR-10, 250 Labels	SelfMatch
Graph Classification	CIFAR10 100k	DGN
Semi-Supervised Image Classification	CIFAR-10, 1000 Labels	MixMatch
Anomaly Detection	One-class CIFAR-10	CSI
Stochastic Optimization	CIFAR-100 WRN-28-10 - 200 Epochs	AvaGrad
Stochastic Optimization	CIFAR-10 WRN-28-10 - 200 Epochs	Adam
Out-of-Distribution Detection	CIFAR-10	ResNet 34 + FSSD
Neural Network Compression	CIFAR-10	ShuffleNet – Quantised
Semi-Supervised Image Classification	CIFAR-10, 40 Labels	SelfMatch
Semi-Supervised Image Classification	cifar10, 250 Labels	ReMixMatch
Unsupervised Image Classification	CIFAR-10	RUC
Stochastic Optimization	CIFAR-10 ResNet-18 - 200 Epochs	Lookahead
Out-of-Distribution Detection	CIFAR-10 vs CIFAR-100	Wide 40-2 + OECC
Network Pruning	CIFAR-10	TAS-pruned ResNet-110
Semi-Supervised Image Classification	CIFAR-10, 2000 Labels	MixMatch
Robust classification	CIFAR-10	ResNet-44 w/ Robust Loss, Adv. Training, and HHReLU
Stochastic Optimization	CIFAR-10	Resnet18
Density Estimation	CIFAR-10	MAF
Small Data Image Classification	cifar10, 10 labels	VAE
Out-of-Distribution Detection	CIFAR-100 vs CIFAR-10	WRN 40-2 + OECC
Long-tail Learning	CIFAR-10-LT (ρ=100)	smDRAGON
Long-tail Learning	CIFAR-10-LT (ρ=10)	smDRAGON
Anomaly Detection	CIFAR-10	Self-Supervised DeepSVDD
Quantization	CIFAR-10	DTQ
Image Classification	cifar-10,4000	WRN-28-2 + UDA+AutoDropout
Density Estimation	CIFAR-10 (Conditional)	MAF
Semi-Supervised Image Classification	CIFAR-10, 20 Labels	SimCLR
Semi-Supervised Image Classification	CIFAR-10, 80 Labels	SimCLR
Semi-Supervised Image Classification	CIFAR-10, 500 Labels	MixMatch
Adversarial Defense	CIFAR-10	PCL
Small Data Image Classification	CIFAR-10, 250 Labels	GLICO
Small Data Image Classification	CIFAR-10, 500 Labels	GLICO
Hard-label Attack	CIFAR-10	RayS