CIFAR-10 (Canadian Institute for Advanced Research, 10 classes)

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.

Task	Dataset Variant	Best Model
Image Classification	CIFAR-10	efficient adaptive ensembling
Image Generation	CIFAR-10	SIMS
Long-tail Learning	CIFAR-10-LT (ρ=10)	GLMC+MaxNorm
Semi-Supervised Image Classification	CIFAR-10, 4000 Labels	SemCo
Neural Architecture Search	CIFAR-10	NAT-M4
Anomaly Detection	One-class CIFAR-10	CLIP
Image Clustering	CIFAR-10	TURTLE
Long-tail Learning	CIFAR-10-LT (ρ=100)	GLMC+MaxNorm
Conditional Image Generation	CIFAR-10	EDM-G++
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
Graph Classification	CIFAR10 100k	NeuralWalker
Out-of-Distribution Detection	CIFAR-10 vs CIFAR-100	DHM
Density Estimation	CIFAR-10	MuLAN
Out-of-Distribution Detection	CIFAR-10	DHM
Dataset Distillation - 1IPC	CIFAR-10	PODD
Unsupervised Image Classification	CIFAR-10	TURTLE
Semi-Supervised Image Classification	CIFAR-10, 1000 Labels	MixMatch
Adversarial Defense	CIFAR-10	WRN-28-10
Active Learning	CIFAR10 (10,000)	TypiClust
Personalized Federated Learning	CIFAR-10	pFedHN-PC
Sequential Image Classification	noise padded CIFAR-10	FlexTCN-6
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly	CIFAR-10	LVAD
Small Data Image Classification	CIFAR-10, 500 Labels	ChimeraMix+AutoAugment
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly	CIFAR-10	LVAD
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly	CIFAR-10	LVAD
Stochastic Optimization	CIFAR-10 WRN-28-10 - 200 Epochs	Adam
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly	CIFAR-10	Shell-Renormalized
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly	cifar10	Shell-Renormalized
Anomaly Detection	Leave-One-Class-Out CIFAR-10	BCE-CLIP
Classification with Binary Weight Network	CIFAR-10	WRN-28-10
Classification with Binary Neural Network	CIFAR-10	BATS
Sparse Learning and binarization	CIFAR-10	SBNN-50%
Small Data Image Classification	CIFAR-10, 1000 Labels	ChimeraMix+AutoAugment
Neural Network Compression	CIFAR-10	ShuffleNet – Quantised
Small Data Image Classification	CIFAR-10, 100 Labels	ChimeraMix+AutoAugment
Open-World Semi-Supervised Learning	CIFAR-10	OpenLDN
Data Augmentation	CIFAR-10	Shake-Shake
Stochastic Optimization	CIFAR-10 ResNet-18 - 200 Epochs	SGD - cosine LR schedule
Adversarial Attack	CIFAR-10	Xu et al.
Image Classification	CIFAR-10 (with noisy labels)	PGDF
Semi-Supervised Image Classification	CIFAR-10, 2000 Labels	MixMatch
Provable Adversarial Defense	CIFAR-10	SLL X-Large
Adversarial Robustness	CIFAR-10	Mixed classifier
Network Pruning	CIFAR-10	TAS-pruned ResNet-110
Semi-Supervised Image Classification	cifar10, 250 Labels	ReMixMatch
Semi-Supervised Image Classification	cifar-10, 10 Labels	BOSS
Robust classification	CIFAR-10	ResNet-110 w/ Adv. Training
Semi-Supervised Image Classification	CIFAR-10, 20 Labels	MutexMatch
Image Generation	CIFAR-10 (20% data)	DiffAugment-CR-BigGAN
Image Generation	CIFAR-10 (10% data)	DiffAugment-StyleGAN2
Image Classification with Label Noise	CIFAR-10, 20% IDN	CORES2*
Image Classification with Label Noise	CIFAR-10, 40% IDN	CORES2*
Image Classification with Label Noise	CIFAR-10, 60% IDN	CORES2*
Clean-label Backdoor Attack (0.05%)	CIFAR-10	GoogLeNet
Supervised Image Retrieval	CIFAR-10	SSB-VAE
Stochastic Optimization	CIFAR-10	Resnet18
Binarization	CIFAR-10	WRN-28-10
Neural Architecture Search	NATS-Bench Size, CIFAR-10	BossNAS
Image Classification	CIFAR-10 Image Classification	ASF-former-S
Self-Supervised Learning	cifar10	ResNet50
Semi-Supervised Image Classification	CIFAR-10, 80 Labels	MutexMatch
Small Data Image Classification	cifar10, 10 labels	VAE
Zero-Shot Learning	CIFAR-10	ZLaP*
ROLSSL-Consistent	CIFAR-10	DPLA
ROLSSL-Reversed	CIFAR-10	DPLA
ROLSSL-Uniform	CIFAR-10	DPLA
Quantization	CIFAR-10	3DCNN_VIVA_3
Semi-Supervised Image Classification (Cold Start)	CIFAR-10, 100 Labels	SimCLR-kmediods-PAWS
Nature-Inspired Optimization Algorithm	CIFAR-10	Position-wise optimizer
Image Classification	CIFAR-10, 40% Symmetric Noise	FaMUS
Image Classification	CIFAR-10, 60% Symmetric Noise	MentorMix
Out-of-Distribution Detection	cifar10	Wideresnet 40
Hard-label Attack	CIFAR-10	RayS
Long-tail Learning on CIFAR-10-LT (ρ=100)	CIFAR-10-LT (ρ=100)	BCL
Density Estimation	CIFAR-10 (Conditional)	MAF
Semi-Supervised Image Classification	CIFAR-10, 100 Labels	SimCLR-kmediods-PAWS
Semi-Supervised Image Classification	CIFAR-10, 30 Labels	SimCLR-kmediods-PAWS
Image Compression	CIFAR-10	Lossyless Compressor
Semi-Supervised Image Classification (Cold Start)	CIFAR-10, 40 Labels	FixMatch-USL-T
Partial Label Learning	CIFAR-10 (partial ratio 0.1)	ILL
Partial Label Learning	CIFAR-10 (partial ratio 0.3)	ILL
Partial Label Learning	CIFAR-10 (partial ratio 0.5)	ILL
Continual Learning	Split CIFAR-10 (5 tasks)	H$^{2}$
Semi-Supervised Image Classification	CIFAR-10, 500 Labels	MixMatch
Contrastive Learning	CIFAR-10	IPCL
Self-Supervised Learning	CIFAR-10	CorInfomax
Graph Classification	CIFAR-10	CKGCN
Transductive Zero-Shot Classification	CIFAR-10	ZLaP
Semi-Supervised Image Classification (Cold Start)	CIFAR-10, 30 Labels	SimCLR-kmediods-PAWS
Image Classification with Label Noise	CIFAR-10, 30% Asymmetric Noise	CORES2*
Image Classification with Label Noise	CIFAR-10, 20% Asymmetric Noise	CORES2*
Image Classification with Label Noise	CIFAR-10, 60% Symmetric Noise	CORES2*
Image Classification with Label Noise	CIFAR-10, 40% Symmetric Noise	CORES2*
Image Classification with Human Noise	CIFAR-10, Human Noise	HOC
Domain-IL Continual Learning	Cifar10 (5 tasks)	HVCL
Model Poisoning	CIFAR-10	ADA
Image Retrieval	CIFAR-10	Custom: 3 conv + 2 fcn
Image Classification with Label Noise	CIFAR-10	PropMix
Image Classification	cifar10	SAM
Novel Class Discovery	cifar10	AutoNovel
Learning with noisy labels	CIFAR-10	ILL
Image Classification	cifar-10,4000	WRN-28-2 + UDA+AutoDropout
Anomaly Detection	CIFAR-10	RCALAD
Small Data Image Classification	CIFAR-10, 250 Labels	GLICO

CIFAR-10 (Canadian Institute for Advanced Research, 10 classes)

Benchmarks Edit Add a new result Link an existing benchmark

Papers

Dataset Loaders Edit Add Remove

Tasks Edit

Similar Datasets

MNIST

STL-10

Fashion-MNIST

SVHN

Usage

License Edit

Modalities Edit

Languages Edit

Benchmarks

Add a new result Link an existing benchmark

Dataset Loaders

Add Remove

Tasks

License

Modalities

Languages