paper-with-me

MNIST

홈페이지 · 논문 7,651편

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. Source: http://yann.lecun.com/exdb/mnist/ Image Source: https://en.wikipedia.org/wiki/MNIST_database#/media/File:MnistExamples.png

Images English

벤치마크

Image Classification on MNIST 결과 92개
Video Prediction on Moving MNIST 결과 62개
Sequential Image Classification on Sequential MNIST 결과 30개
Graph Classification on MNIST 결과 26개
Image Clustering on MNIST-full 결과 16개
Unsupervised Image-To-Image Translation on SVNH-to-MNIST 결과 16개
Image Generation on MNIST 결과 15개
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly on MNIST 결과 15개
Domain Adaptation on MNIST-to-USPS 결과 14개
Domain Adaptation on USPS-to-MNIST 결과 14개
Image Clustering on MNIST-test 결과 11개
Unsupervised Image Classification on MNIST 결과 10개
Domain Adaptation on SVNH-to-MNIST 결과 9개
Anomaly Detection on MNIST 결과 6개
Clustering Algorithms Evaluation on MNIST 결과 6개
Density Estimation on MNIST 결과 6개
Superpixel Image Classification on 75 Superpixel MNIST 결과 6개
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly on MNIST 결과 5개
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly on MNIST 결과 5개
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly on MNIST 결과 5개
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly on MNIST 결과 5개
Image Clustering on MNIST 결과 3개
One-Shot Learning on MNIST 결과 3개
Rotated MNIST on Rotated MNIST 결과 3개
Adversarial Defense on MNIST 결과 2개
Continuously Indexed Domain Adaptation on Indexed Rotating MNIST 결과 2개
Domain Adaptation on Rotating MNIST 결과 2개
Fine-Grained Image Classification on MNIST 결과 2개
Handwritten Digit Recognition on MNIST 결과 2개
Image Classification on Noisy MNIST (AWGN) 결과 2개
Image Classification on Noisy MNIST (Contrast) 결과 2개
Image Classification on Noisy MNIST (Motion) 결과 2개
Nature-Inspired Optimization Algorithm on MNIST 결과 2개
Neural Architecture Search on MNIST 결과 2개
Personalized Federated Learning on MNIST 결과 2개
Unsupervised Anomaly Detection on MNIST 결과 2개
Anomaly Detection on MNIST-test 결과 1개
Continual Learning on Rotated MNIST 결과 1개
Core set discovery on MNIST 결과 1개
Deep Clustering on MNIST 결과 1개
General Classification on MNIST 결과 1개
Network Pruning on MNIST 결과 1개
Stochastic Optimization on MNIST 결과 1개
Structured Prediction on MNIST 결과 1개