CIFAR-10

Introduced by Krizhevsky et al. in Learning multiple layers of features from tiny images

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	ViT-H/14
Image Generation	CIFAR-10	LSGM
Semi-Supervised Image Classification	CIFAR-10, 4000 Labels	LaplaceNet
Neural Architecture Search	CIFAR-10	NAT-M4
Conditional Image Generation	CIFAR-10	StyleGAN2 + DiffAugment + D2D-CE
Image Clustering	CIFAR-10	SPICE*
Anomaly Detection	One-class CIFAR-10	Transformaly
Neural Architecture Search	CIFAR-10 Image Classification	NAT-M4
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ViT
Semi-Supervised Image Classification	CIFAR-10, 250 Labels	Dash
Out-of-Distribution Detection	CIFAR-100 vs CIFAR-10	Ensemble of ViTs
Out-of-Distribution Detection	CIFAR-10 vs CIFAR-100	R+ViT finetuned on CIFAR-10
Graph Classification	CIFAR10 100k	DGN
Semi-Supervised Image Classification	CIFAR-10, 1000 Labels	MixMatch
Semi-Supervised Image Classification	CIFAR-10, 40 Labels	FlexMatch
Sequential Image Classification	noise padded CIFAR-10	FlexTCN-6
Out-of-Distribution Detection	CIFAR-10	Wide ResNet 40x2
Stochastic Optimization	CIFAR-100 WRN-28-10 - 200 Epochs	AvaGrad
Stochastic Optimization	CIFAR-10 WRN-28-10 - 200 Epochs	Adam
Anomaly Detection	CIFAR-10	IGD
Long-tail Learning	CIFAR-10-LT (ρ=10)	TADE
Neural Network Compression	CIFAR-10	ShuffleNet – Quantised
Personalized Federated Learning	CIFAR-10	pFedHN-PC
Adversarial Defense	CIFAR-10	Ours
Long-tail Learning	CIFAR-10-LT (ρ=100)	TADE
Classification with Binary Weight Network	CIFAR-10	WRN-28-10
Network Pruning	CIFAR-10	TAS-pruned ResNet-110
Semi-Supervised Image Classification	cifar10, 250 Labels	ReMixMatch
Stochastic Optimization	CIFAR-10 ResNet-18 - 200 Epochs	Lookahead
Unsupervised Image Classification	CIFAR-10	RUC
Small Data Image Classification	CIFAR-10, 500 Labels	LearnableScatteringNetwork+WRN
Density Estimation	CIFAR-10	MAF
Semi-Supervised Image Classification	CIFAR-10, 2000 Labels	MixMatch
Robust classification	CIFAR-10	ResNet-44 w/ Robust Loss, Adv. Training, and HHReLU
Adversarial Attack	CIFAR-10	Xu et al.
Small Data Image Classification	CIFAR-10, 1000 Labels	WRN
Image Classification	CIFAR-10 (with noisy labels)	C2D
Small Data Image Classification	cifar10, 10 labels	VAE
Stochastic Optimization	CIFAR-10	Resnet18
Classification with Binary Neural Network	CIFAR-10	MPT-1/1
Binarization	CIFAR-10	WRN-28-10
Adversarial Robustness	CIFAR-10	Stochastic-LWTA/PGD/WideResNet-34-10
Quantization	CIFAR-10	3DCNN_VIVA_3
Semi-Supervised Image Classification	CIFAR-10, 20 Labels	CoMatch
Image Classification	CIFAR10	vit-base-beans
Parameter Prediction	CIFAR10	GHN-2
Image Compression	CIFAR-10	Lossyless Compressor
Small Data Image Classification	CIFAR-10, 250 Labels	GLICO
Hard-label Attack	CIFAR-10	RayS
Image Classification	cifar-10,4000	WRN-28-2 + UDA+AutoDropout
Semi-Supervised Image Classification	CIFAR-10, 80 Labels	SimCLR
Unsupervised Anomaly Detection	CIFAR-10	3 Layers
Density Estimation	CIFAR-10 (Conditional)	MAF
Semi-Supervised Image Classification	CIFAR-10, 500 Labels	MixMatch