Datasets › EMNIST

EMNIST (Extended MNIST)

Introduced by Gregory Cohen et al. in EMNIST: an extension of MNIST to handwritten letters17 Feb 2017 archive 2025-07-28

EMNIST (extended MNIST) has 4 times more data than MNIST. It is a set of handwritten digits with a 28 x 28 format.

Source: Domain Discrepancy Measure for Complex Models in Unsupervised Domain Adaptation Image Source: https://arxiv.org/pdf/1803.01900.pdf

Benchmarks archive 2025-07-28

All 10 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 EMNIST-Balanced EMNIST-mobile Accuracy 91.48 Efficient Global Neural Architecture Search siddikui/Efficient-Macro-Micro-NAS 20 Compare
Image Classification EMNIST-Letters WaveMixLite-112/16 Accuracy 95.96 WaveMix: A Resource-efficient Neural Network for Image Analysis pranavphoenix/WaveMix 11 Compare
Image Classification EMNIST-Digits WaveMixLite-112/16 Accuracy (%) 99.82 WaveMix: A Resource-efficient Neural Network for Image Analysis pranavphoenix/WaveMix 7 Compare
Dimensionality Reduction EMNIST UDRN Classification Accuracy 71.1 UDRN: Unified Dimensional Reduction Neural Network for... — 2 Compare
Image Clustering EMNIST-Balanced AE+SNNL Accuracy 0.792 Improving k-Means Clustering Performance with... gitlab.com/afagarap/pt-snnl 2 Compare
Fine-Grained Image Classification EMNIST-Digits VGG-5 Accuracy 99.82 ProgressiveSpinalNet architecture for FC layers praveenchopra/ProgressiveSpinalNet 1 Compare
Fine-Grained Image Classification EMNIST-Letters VGG-5 Accuracy 95.86 ProgressiveSpinalNet architecture for FC layers praveenchopra/ProgressiveSpinalNet 1 Compare
Image Classification EMNIST-Byclass WaveMixLite-128/7 Accuracy 88.43 WaveMix: A Resource-efficient Neural Network for Image Analysis pranavphoenix/WaveMix 1 Compare
Image Classification EMNIST-Bymerge WaveMixLite-128/16 Accuracy 91.80 WaveMix: A Resource-efficient Neural Network for Image Analysis pranavphoenix/WaveMix 1 Compare
Image Generation EMNIST-Letters Spiking-Diffusion FID 67.41 Spiking-Diffusion: Vector Quantized Discrete Diffusion... Arktis2022/Spiking-Diffusion 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 19 · with a code link: 14 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (2 of 19 with a benchmark row: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 19 of 19 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 264. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Efficient Global Neural Architecture Search 1 2 8 Feb 2025 not harvested
Regularizing cross entropy loss via minimum entropy and K-L divergence 1 2 23 Jan 2025 not harvested
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning 0 4 22 Jan 2024 not harvested
Parametric Matrix Models 0 2 22 Jan 2024 not harvested
Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks 1 1 20 Aug 2023 not harvested
A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems 1 1 15 Sep 2022 not harvested
UDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projection 0 1 8 Jul 2022 not harvested
WaveMix: A Resource-efficient Neural Network for Image Analysis 1 5 28 May 2022 not harvested
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems 1 1 25 May 2022 not harvested
ProgressiveSpinalNet architecture for FC layers 1 2 21 Mar 2021 not harvested
Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders 2 1 1 Dec 2020 not harvested
SpinalNet: Deep Neural Network with Gradual Input 3 8 7 Jul 2020 not harvested
Improving k-Means Clustering Performance with Disentangled Internal Representations 1 3 5 Jun 2020 not harvested
Efficient Neural Vision Systems Based on Convolutional Image Acquisition 0 3 1 Jun 2020 not harvested
TextCaps : Handwritten Character Recognition with Very Small Datasets 3 1 17 Apr 2019 not harvested
Handwritten digit and letter recognition using hybrid dwt-dct with knn and svm classifier 0 2 18 Aug 2018 not harvested
Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks 1 1 21 May 2018 not harvested
Dynamic Routing Between Capsules 77 1 26 Oct 2017 official (archive's flag): 1 ran · 75 ran (of which 0 constructed an object rather than computing a result; 58 with no instrument failure: 0 honoured, 0 violated, 58 with no contract checked; 17 where Syntology's instrument failed) · 43 unverified (13 pointer-only for licence)
EMNIST: an extension of MNIST to handwritten letters 31 6 17 Feb 2017 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)

Dataset loaders archive 2025-07-28

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

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • EMNIST-Letters
  • EMNIST-Digits
  • EMNIST-Balanced
  • EMNIST
  • EMNIST-Byclass
  • EMNIST-Bymerge

6 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