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	EDM-G++
Semi-Supervised Image Classification	CIFAR-10, 4000 Labels	SemCo
Neural Architecture Search	CIFAR-10	NAT-M4
Anomaly Detection	One-class CIFAR-10	CLIP
Conditional Image Generation	CIFAR-10	EDM-G++
Image Clustering	CIFAR-10	SPICE*
Semi-Supervised Image Classification	CIFAR-10, 250 Labels	Dash
Neural Architecture Search	CIFAR-10 Image Classification	NAT-M4
Semi-Supervised Image Classification	CIFAR-10, 40 Labels	FreeMatch
Out-of-Distribution Detection	CIFAR-100 vs CIFAR-10	DHM
Out-of-Distribution Detection	CIFAR-10 vs CIFAR-100	DHM
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ViT
Graph Classification	CIFAR10 100k	ARGNP
Long-tail Learning	CIFAR-10-LT (ρ=100)	OPeN
Image Classification	cifar10	BEiT-finetuned
Out-of-Distribution Detection	CIFAR-10	DHM
Semi-Supervised Image Classification	CIFAR-10, 1000 Labels	MixMatch
Sequential Image Classification	noise padded CIFAR-10	FlexTCN-6
Personalized Federated Learning	CIFAR-10	pFedHN-PC
Long-tail Learning	CIFAR-10-LT (ρ=10)	TADE
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly	cifar10	Shell-Renormalized
Sparse Learning and binarization	CIFAR-10	SBNN-50%
Classification with Binary Weight Network	CIFAR-10	WRN-28-10
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly	CIFAR-10	LVAD
Stochastic Optimization	CIFAR-10 WRN-28-10 - 200 Epochs	Adam
Stochastic Optimization	CIFAR-100 WRN-28-10 - 200 Epochs	AvaGrad
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly	CIFAR-10	LVAD
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly	CIFAR-10	LVAD
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly	CIFAR-10	Shell-Renormalized
Small Data Image Classification	CIFAR-10, 500 Labels	ChimeraMix+AutoAugment
Small Data Image Classification	CIFAR-10, 1000 Labels	ChimeraMix+AutoAugment
Adversarial Defense	CIFAR-10	Ours
Neural Network Compression	CIFAR-10	ShuffleNet – Quantised
Density Estimation	CIFAR-10	MAF
Semi-Supervised Image Classification	CIFAR-10, 2000 Labels	MixMatch
Network Pruning	CIFAR-10	TAS-pruned ResNet-110
Semi-Supervised Image Classification	cifar10, 250 Labels	ReMixMatch
Stochastic Optimization	CIFAR-10 ResNet-18 - 200 Epochs	SGD - cosine LR schedule
Unsupervised Image Classification	CIFAR-10	RUC
Robust classification	CIFAR-10	ResNet-44 w/ Robust Loss, Adv. Training, and HHReLU
Semi-Supervised Image Classification	CIFAR-10, 20 Labels	MutexMatch
Classification with Binary Neural Network	CIFAR-10	AdaBin
Adversarial Attack	CIFAR-10	Xu et al.
Image Classification	CIFAR-10 (with noisy labels)	C2D
Clean-label Backdoor Attack (0.05%)	CIFAR-10	GoogLeNet
Stochastic Optimization	CIFAR-10	Resnet18
Binarization	CIFAR-10	WRN-28-10
Quantization	CIFAR-10	3DCNN_VIVA_3
Adversarial Robustness	CIFAR-10	Stochastic-LWTA/PGD/WideResNet-34-10
Nature-Inspired Optimization Algorithm	CIFAR-10	Position-wise optimizer
Semi-Supervised Image Classification	CIFAR-10, 80 Labels	MutexMatch
Small Data Image Classification	cifar10, 10 labels	VAE
Model Poisoning	CIFAR-10	ADA
Image Retrieval	CIFAR-10	Custom: 3 conv + 2 fcn
Image Classification with Label Noise	CIFAR-10	PropMix
Image Compression	CIFAR-10	Lossyless Compressor
Image Classification	cifar-10,4000	WRN-28-2 + UDA+AutoDropout
Novel Class Discovery	cifar10	NCL
Learning with noisy labels	CIFAR-10	InstanceGM
Small Data Image Classification	CIFAR-10, 250 Labels	GLICO
Hard-label Attack	CIFAR-10	RayS
Density Estimation	CIFAR-10 (Conditional)	MAF
Image Classification	CIFAR10_CATS	CatsNet
Out-of-Distribution Detection	cifar10	Wideresnet 40
Semi-Supervised Image Classification	CIFAR-10, 500 Labels	MixMatch