MNIST

Introduced by LeCun et al. in Gradient-based learning applied to document recognition

The MNIST database (Modified National Institute of Standards and Technology database) is a large collection of handwritten digits. It has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger NIST Special Database 3 (digits written by employees of the United States Census Bureau) and Special Database 1 (digits written by high school students) which contain monochrome images of handwritten digits. The digits have been size-normalized and centered in a fixed-size image. The original black and white (bilevel) images from NIST were size normalized to fit in a 20x20 pixel box while preserving their aspect ratio. The resulting images contain grey levels as a result of the anti-aliasing technique used by the normalization algorithm. the images were centered in a 28x28 image by computing the center of mass of the pixels, and translating the image so as to position this point at the center of the 28x28 field.

Task	Dataset Variant	Best Model
Image Classification	MNIST	Branching/Merging CNN + Homogeneous Vector Capsules
Sequential Image Classification	Sequential MNIST	SMPConv
Video Prediction	Moving MNIST	SimVP+gSTA-Sx10
Image Clustering	MNIST-full	SPC
Image Generation	MNIST	Locally Masked PixelCNN
Domain Adaptation	MNIST-to-USPS	FACT
Domain Adaptation	USPS-to-MNIST	FACT
Image Clustering	MNIST-test	DynAE
Unsupervised MNIST	MNIST	IIC
Domain Adaptation	SVNH-to-MNIST	SRDA
Unsupervised Image Classification	MNIST	IIC
Graph Classification	MNIST	Exphormer
Superpixel Image Classification	75 Superpixel MNIST	Dynamic Reduction Network
Anomaly Detection	MNIST	GAN-based Anomaly Detection in Imbalance Problems
Clustering Algorithms Evaluation	MNIST	GIT
Density Estimation	MNIST	Identity
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly	MNIST	LVAD
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly	MNIST	LVAD
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly	MNIST	LVAD
Sparse Learning and binarization	MNIST	SBNN-5%
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly	MNIST	LVAD
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly	MNIST	LVAD
Unsupervised Image-To-Image Translation	SVNH-to-MNIST	DANN
Rotated MNIST	Rotated MNIST	Sim2-CNN
Handwritten Digit Recognition	MNIST	CNN
Image Classification	Noisy MNIST (AWGN)	PCGAN-CHAR
Image Classification	Noisy MNIST (Motion)	PCGAN-CHAR
Image Classification	Noisy MNIST (Contrast)	PCGAN-CHAR
Domain Adaptation	Rotating MNIST	PCIDA
Continuously Indexed Domain Adaptation	Indexed Rotating MNIST	PCIDA
Adversarial Defense	MNIST	Defense GAN
Adversarial Defense against FGSM Attack	MNIST	Defense GAN
Nature-Inspired Optimization Algorithm	MNIST	Gradient descent optimizer
Personalized Federated Learning	MNIST	SuPerFed-LM
Continual Learning	Rotated MNIST	Model Zoo-Continual
Core set discovery	MNIST	EvoCore
General Classification	MNIST	CAE
One-Shot Learning	MNIST	Siamese Neural Network
Deep Clustering	MNIST	DEKM
Model Poisoning	MNIST	ADA
Malicious Detection	MNIST	FAIR-BFL
Network Pruning	MNIST	FFN-ShapleyPruned
Unsupervised Anomaly Detection	MNIST	LVAD
Stochastic Optimization	MNIST	MLP
Multiview Clustering	MNIST	MCoCo
Structured Prediction	MNIST	CVAE
Image Clustering	MNIST	CoHiClust
Hard-label Attack	MNIST	RayS
Fine-Grained Image Classification	MNIST	Vanilla FC layer only
Anomaly Detection	MNIST-test	OGNET
Neural Architecture Search	MNIST	Sparse Neural Network
Classification with Binary Weight Network	MNIST	LeNet5

MNIST

Benchmarks Edit Add a new result Link an existing benchmark

Papers

Dataset Loaders Edit Add Remove

Tasks Edit

Similar Datasets

USPS

SVHN

Fashion-MNIST

CIFAR-10

Usage

License Edit

Modalities Edit

Languages Edit

Benchmarks

Add a new result Link an existing benchmark

Dataset Loaders

Add Remove

Tasks

License

Modalities

Languages