mlsanityData to 7 Oct 2026

EMNIST: an extension of MNIST to handwritten letters

arXiv 1702.05373 ↗First posted 17 Feb 2017cs.CVcited by 212

Not on the map. Why?

Abstract (arXiv)

The MNIST dataset has become a standard benchmark for learning, classification and computer vision systems. Contributing to its widespread adoption are the understandable and intuitive nature of the task, its relatively small size and storage requirements and the accessibility and ease-of-use of the database itself. The MNIST database was derived from a larger dataset known as the NIST Special Database 19 which contains digits, uppercase and lowercase handwritten letters. This paper introduces a variant of the full NIST dataset, which we have called Extended MNIST (EMNIST), which follows the same conversion paradigm used to create the MNIST dataset. The result is a set of datasets that constitute a more challenging classification tasks involving letters and digits, and that shares the same image structure and parameters as the original MNIST task, allowing for direct compatibility with all existing classifiers and systems. Benchmark results are presented along with a validation of the conversion process through the comparison of the classification results on converted NIST digits and the MNIST digits.

Key facts. Cited by 212 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 46; 2022: 50; 2023: 35; 2024: 36; 2025: 26; 2026: 18.

212 papers.

Sort:

By area:

  1. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  2. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  3. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 137
  4. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 135
  5. 2022Federated Learning with Partial Model Personalizationcited by 114
  6. 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 112
  7. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  8. 2021Learning Optimal Conformal Classifierscited by 108
  9. 2021On the Role of Neural Collapse in Transfer Learningcited by 100
  10. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  11. 2021What Do We Mean by Generalization in Federated Learning?cited by 62
  12. 2021Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restorationcited by 50
38 more
  1. 2024Schr"odinger Bridge Flow for Unpaired Data Translationcited by 47
  2. 2022How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularizationcited by 40
  3. 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
  4. 2021One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learningcited by 39
  5. 2022NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networkscited by 38
  6. 2021Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learningcited by 36
  7. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  8. 2021Property Inference Attacks Against GANscited by 32
  9. 2023Learning to Warm-Start Fixed-Point Optimization Algorithmscited by 32
  10. 2023Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translationcited by 32
  11. 2023On the Convergence of Federated Averaging with Cyclic Client Participationcited by 31
  12. 2021Explaining Latent Representations with a Corpus of Examplescited by 30
  13. 2022Learning from Label Proportions by Learning with Label Noisecited by 30
  14. 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
  15. 2022Federated Learning with Position-Aware Neuronscited by 24
  16. 2022Gradient Masked Averaging for Federated Learningcited by 22
  17. 2021Learning with Algorithmic Supervision via Continuous Relaxationscited by 21
  18. 2024C2M3: Cycle-Consistent Multi-Model Mergingcited by 20
  19. 2021Learning from Similarity-Confidence Datacited by 19
  20. 2021Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Becited by 19
  21. 2022PAC-Bayesian Offline Contextual Bandits With Guaranteescited by 19
  22. 2021Adversarial training in communication constrained federated learningcited by 17
  23. 2022UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANscited by 16
  24. 2021Estimating informativeness of samples with Smooth Unique Informationcited by 15
  25. 2021Evaluating State-of-the-Art Classification Models Against Bayes Optimalitycited by 15
  26. 2023Compress Then Test: Powerful Kernel Testing in Near-linear Timecited by 14
  27. 2021Efficient and Private Federated Learning with Partially Trainable Networkscited by 13
  28. 2021FedLess: Secure and Scalable Federated Learning Using Serverless Computingcited by 13
  29. 2022Super-resolution image display using diffractive decoderscited by 13
  30. 2023JaxPruner: A concise library for sparsity researchcited by 13
  31. 2024Personalized Federated Learning via Feature Distribution Adaptationcited by 13
  32. 2021FedPrune: Towards Inclusive Federated Learningcited by 12
  33. 2022A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimizationcited by 11
  34. 2021Meta-Learning Bidirectional Update Rulescited by 10
  35. 2023VTAE: Variational Transformer Autoencoder with Manifolds Learningcited by 10
  36. 2023FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategycited by 10
  37. 2021The Uncanny Similarity of Recurrence and Depthcited by 9
  38. 2021Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoningcited by 9

50 most cited of 212 All 212 (JSON)