</> Code with Papers by Syntology

Datasets › Fashion-MNIST

Fashion-MNIST

Introduced by Han Xiao et al. in Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms1 Jan 2017 archive 2025-07-28

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

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 15 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Classification Fashion-MNIST PreAct-ResNet18 + FMix Percentage error 3.64 FMix: Enhancing Mixed Sample Data Augmentation PaddlePaddle/PaddleClas +4 34 Compare
Image Clustering Fashion-MNIST PRCut (DinoV2) Accuracy 0.791 Deep Clustering via Probabilistic Ratio-Cut Optimization ayghri/prcut 13 Compare
Anomaly Detection Fashion-MNIST GAN based Anomaly Detection in Imbalance Problems ROC AUC 98.6 GAN-based Anomaly Detection in Imbalance Problems — 12 Compare
Image Generation Fashion-MNIST GLF+perceptual loss (ours) FID 10.3 Generative Latent Flow rakhimovv/GenerativeLatentFlow 7 Compare
Clustering Algorithms Evaluation Fashion-MNIST AE+GIT ARI 49% Git: Clustering Based on Graph of Intensity Topology gaozhangyang/DGC +3 6 Compare
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly Fashion-MNIST Isolation Forest AUC-ROC 0.908 Isolation forest — 5 Compare
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly Fashion-MNIST IF AUC-ROC 0.889 Isolation forest — 5 Compare
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly Fashion-MNIST Isolation Forest AUC-ROC 0.917 Isolation forest — 5 Compare
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly Fashion-MNIST IF AUC-ROC 0.889 Isolation forest — 5 Compare
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly Fashion-MNIST IF AUC-ROC 0.915 Isolation forest — 5 Compare
Domain Generalization Rotated Fashion-MNIST MatchDG Accuracy 82.8 Domain Generalization using Causal Matching microsoft/robustdg 2 Compare
Out-of-Distribution Detection Fashion-MNIST PAE AUROC 0.997 Probabilistic Autoencoder VMBoehm/PAE +3 2 Compare
General Classification Fashion-MNIST CAE Accuracy 67.7 Concrete Autoencoders for Differentiable Feature... mfbalin/Concrete-Autoencoders +1 1 Compare
Outlier Detection Fashion-MNIST PAE AUROC 0.997 Probabilistic Autoencoder VMBoehm/PAE +3 1 Compare
Unsupervised Anomaly Detection Fashion-MNIST RSRAE AUC (outlier ratio = 0.5) 0.833 Robust Subspace Recovery Layer for Unsupervised Anomaly Detection dmzou/RSRAE +1 1 Compare

Papers archive 2025-07-28

30 shown of 59 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 3,202. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Deep Clustering via Probabilistic Ratio-Cut Optimization 1 1 1 Feb 2025 not harvested
Real-valued continued fraction of straight lines 1 1 16 Dec 2024 not harvested
Vision Eagle Attention: a new lens for advancing image classification 1 2 15 Nov 2024 not harvested
Learning local discrete features in explainable-by-design convolutional neural networks 1 1 31 Oct 2024 not harvested
Learning in Wilson-Cowan model for metapopulation 1 2 24 Jun 2024 not harvested
The VampPrior Mixture Model 1 1 6 Feb 2024 not harvested
A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification 1 1 1 Feb 2024 not harvested
Towards Physical Plausibility in Neuroevolution Systems 1 2 31 Jan 2024 not harvested
Parametric Matrix Models 0 2 22 Jan 2024 not harvested
TMComposites: Plug-and-Play Collaboration Between Specialized Tsetlin Machines 1 1 9 Sep 2023 not harvested
Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks 1 1 20 Aug 2023 not harvested
Contrastive Hierarchical Clustering 1 1 3 Mar 2023 not harvested
Personalized Federated Learning with Hidden Information on Personalized Prior 0 1 19 Nov 2022 not harvested
Locally varying distance transform for unsupervised visual anomaly detection 1 5 23 Oct 2022 not harvested
Online Training Through Time for Spiking Neural Networks 1 1 9 Oct 2022 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image Classification 1 1 19 Jul 2022 not harvested
Star algorithm for NN ensembling 1 1 1 Jun 2022 not harvested
Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks 1 2 30 May 2022 ran 0 of 2 samples (2 unverified)
WaveMix: A Resource-efficient Neural Network for Image Analysis 1 1 28 May 2022 not harvested
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters 1 1 29 Mar 2022 not harvested
Anomaly Detection via Reverse Distillation from One-Class Embedding 5 1 26 Jan 2022 ran 14 of 18 samples (4 unverified; 15 pointer-only for licence)
Preventing Manifold Intrusion with Locality: Local Mixup 1 1 12 Jan 2022 not harvested
Git: Clustering Based on Graph of Intensity Topology 4 6 4 Oct 2021 not harvested
Spike time displacement based error backpropagation in convolutional spiking neural networks 0 1 31 Aug 2021 not harvested
Selective Pseudo-label Clustering 1 1 22 Jul 2021 not harvested
DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection 1 1 9 Jun 2021 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
Shell Theory: A Statistical Model of Reality 1 1 28 May 2021 not harvested
Sparse Spiking Gradient Descent 1 2 18 May 2021 not harvested
Deep One-Class Classification via Interpolated Gaussian Descriptor 2 3 25 Jan 2021 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training 0 1 19 Jan 2021 not harvested

The full list of 59 is in the JSON twin.

Dataset loaders archive 2025-07-28

huggingface.co/datasets/fashion_mnisthuggingface/datasetstfpytorchjax
huggingface.co/datasets/zalando-datasets/fashion_mnisthuggingface/datasetstfpytorchjax
pytorch.org/vision/stable/generated/torchvision.datasets.FashionMNIST.htmlpytorch/visionpytorch
zalandoresearch/fashion-mnisttf
docs.voxel51.com/user_guide/dataset_zoo/datasets.html#fashion-mnistvoxel51/fiftyonetfpytorch
docs.activeloop.ai/datasets/fashion-mnist-datasetactiveloopai/Hubtfpytorch
www.tensorflow.org/datasets/catalog/fashion_mnisttensorflow/datasetstfjax
app.layer.ai/layer/fashion_mnistlayerai/sdktfpytorch
gas.graviti.com/dataset/graviti/FashionMNISTGraviti-AI/datasetstfpytorch
gitlab.com/afagarap/pt-datasetspytorch

10 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Image ClassificationImage GenerationAnomaly DetectionImage ClusteringOut-of-Distribution DetectionDomain GeneralizationUnsupervised Anomaly DetectionClustering Algorithms EvaluationOutlier DetectionGeneral ClassificationMultiview ClusteringUnsupervised Anomaly Detection with Specified Settings -- 30% anomalyUnsupervised Anomaly Detection with Specified Settings -- 20% anomalyUnsupervised Anomaly Detection with Specified Settings -- 1% anomalyUnsupervised Anomaly Detection with Specified Settings -- 0.1% anomalyUnsupervised Anomaly Detection with Specified Settings -- 10% anomalyModel Poisoning

License archive 2025-07-28

MIT

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Fashion-MNIST
  • Rotated Fashion-MNIST
  • fashion_mnist

3 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections