Fashion-MNIST

Dataset Information

Modalities

Images

Introduced

2017

License

MIT

Homepage

Official Website

Contents

Overview
Associated Benchmarks
Recent Benchmark Submissions
Research Papers

Overview

Fashion-MNIST is a dataset comprising of 28×28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST shares the same image size, data format and the structure of training and testing splits with the original MNIST.

Source: Generative Probabilistic Novelty Detection with Adversarial Autoencoders
Image Source: https://github.com/zalandoresearch/fashion-mnist

Variants: Fashion-MNIST, Rotated Fashion-MNIST, fashion_mnist

Associated Benchmarks

This dataset is used in 14 benchmarks:

Image Generation - Metrics: FID, Precision, Recall
Anomaly Detection - Metrics: ROC AUC
Outlier Detection - Metrics: AUROC
General Classification - Metrics: Accuracy
Image Clustering - Metrics: Accuracy, NMI
Image Classification - Metrics: Percentage error, Accuracy, Trainable Parameters, NMI, Power consumption
Out-of-Distribution Detection - Metrics: AUROC
Clustering Algorithms Evaluation - Metrics: ARI, F1-score, NMI
Unsupervised Anomaly Detection - Metrics: AUC (outlier ratio = 0.5)
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly - Metrics: AUC-ROC
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly - Metrics: AUC-ROC
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly - Metrics: AUC-ROC
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly - Metrics: AUC-ROC
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly - Metrics: AUC-ROC

Recent Benchmark Submissions

Task	Model	Paper	Date
Image Classification	Continued fraction of straight lines	Real-valued continued fraction of straight …	2024-12-16
Image Classification	ResNet-18	Vision Eagle Attention: a new …	2024-11-15
Image Classification	ResNet-18 + Vision Eagle Attention	Vision Eagle Attention: a new …	2024-11-15
Image Classification	R-ExplaiNet-26	Learning local discrete features in …	2024-10-31
Image Classification	CNN+ Wilson-Cowan model RNN	Learning in Wilson-Cowan model for …	2024-06-24
Image Classification	Wilson-Cowan model RNN	Learning in Wilson-Cowan model for …	2024-06-24
Image Clustering	VMM	The VampPrior Mixture Model	2024-02-06
Image Classification	GECCO	A Single Graph Convolution Is …	2024-02-01
Image Classification	ENERGIZE	Towards Physical Plausibility in Neuroevolution …	2024-01-31
Image Classification	DENSER	Towards Physical Plausibility in Neuroevolution …	2024-01-31
Image Classification	PMM (Parametric Matrix Model)	Parametric Matrix Models	2024-01-22
Image Classification	Convolutional PMM (Parametric Matrix Model)	Parametric Matrix Models	2024-01-22
Image Classification	Tsetlin Machine Composites	TMComposites: Plug-and-Play Collaboration Between Specialized …	2023-09-09
Image Generation	Spiking-Diffusion	Spiking-Diffusion: Vector Quantized Discrete Diffusion …	2023-08-20
Image Clustering	CoHiClust	Contrastive Hierarchical Clustering	2023-03-03
Image Classification	pFedBreD_ns_mg	Personalized Federated Learning with Hidden …	2022-11-19
Image Classification	OTTT	Online Training Through Time for …	2022-10-09
Image Classification	LR-Net	LR-Net: A Block-based Convolutional Neural …	2022-07-19
Image Classification	Star Algorithm on LeNet	Star algorithm for NN ensembling	2022-06-01
Image Classification	FastSNN (CNN)	Robust and accelerated single-spike spiking …	2022-05-30

Research Papers

Recent papers with results on this dataset:

External Links:

Fashion-MNIST

Overview edit

Associated Benchmarks

Recent Benchmark Submissions

Research Papers

Edit Dataset Information

Overview