EMNIST: an extension of MNIST to handwritten letters

Abstract

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.

arXiv commentThe dataset is now available for download from https://www.westernsydney.edu.au/bens/home/reproducible_research/emnist. This link is also included in the revised article

Cited by in corpus (144)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Robust Aggregation for Federated Learning
• Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
• Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges
• Federated Optimization in Heterogeneous Networks
• FedML: A Research Library and Benchmark for Federated Machine Learning
• LEAF: A Benchmark for Federated Settings
• Neuromorphic Deep Learning Machines
• Spectrally-Encoded Single-Pixel Machine Vision Using Diffractive Networks
• Ditto: Fair and Robust Federated Learning Through Personalization
• A Closer Look at Few-shot Classification
• Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Variational Federated Multi-Task Learning
• Controversial stimuli: pitting neural networks against each other as models of human recognition
• Federated Learning for Computationally-Constrained Heterogeneous Devices: A Survey
• Fingertip Detection and Tracking for Recognition of Air-Writing in Videos
• Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models
• Quasi-hyperbolic momentum and Adam for deep learning
• FedMix: Approximation of Mixup under Mean Augmented Federated Learning
• Privacy-preserving Machine Learning through Data Obfuscation
• Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
• Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
• Unseen Class Discovery in Open-world Classification
• Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating
• Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
• Out-of-distribution Detection in Classifiers via Generation
• From the digital data revolution to digital health and digital economy toward a digital society: Pervasiveness of Artificial Intelligence
• Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks
• Why is the Mahalanobis Distance Effective for Anomaly Detection?
• FedScale: Benchmarking Model and System Performance of Federated Learning at Scale
• Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
• SEALion: a Framework for Neural Network Inference on Encrypted Data
• Stochasticity from function -- why the Bayesian brain may need no noise
• Neural Spline Flows
• FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategy
• Learning Generative Models across Incomparable Spaces
• A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids
• Enhancing the Privacy of Federated Learning with Sketching
• Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks
• Continuous learning of spiking networks trained with local rules
• Flexible Dataset Distillation: Learn Labels Instead of Images
• Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning
• Federated Learning with Superquantile Aggregation for Heterogeneous Data
• Device Heterogeneity in Federated Learning: A Superquantile Approach
• Robust Variational Autoencoder
• Robust Watermarking of Neural Network with Exponential Weighting
• Communication-Efficient Federated Distillation
• Deep Amortized Clustering
• Building robust classifiers through generation of confident out of distribution examples
• What Do We Mean by Generalization in Federated Learning?
• Towards Self-Adaptive Metric Learning On the Fly
• Efficient and Private Federated Learning with Partially Trainable Networks
• Learning Optimal Conformal Classifiers
• Fast Real-time Counterfactual Explanations
• Autonomous Deep Learning: A Genetic DCNN Designer for Image Classification
• Invertible Generative Modeling using Linear Rational Splines
• Adaptive Federated Dropout: Improving Communication Efficiency and Generalization for Federated Learning
• Heterogeneous Data-Aware Federated Learning
• A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids
• Anomalous Example Detection in Deep Learning: A Survey
• Bootstrapping Neural Processes
• Federated Learning on Non-IID Data: A Survey
• Fluctuation-dissipation Type Theorem in Stochastic Linear Learning
• Distributed Sketching Methods for Privacy Preserving Regression
• An optical diffractive deep neural network with multiple frequency-channels
• Privacy-preserving Decentralized Aggregation for Federated Learning
• Meta-learning algorithms for Few-Shot Computer Vision
• Evaluating State-of-the-Art Classification Models Against Bayes Optimality
• AutoAssist: A Framework to Accelerate Training of Deep Neural Networks
• Noisy Batch Active Learning with Deterministic Annealing
• A needle-based deep-neural-network camera
• Learning with Algorithmic Supervision via Continuous Relaxations
• BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty
• Assessing Intelligence in Artificial Neural Networks
• Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization
• Information Theoretic Meta Learning with Gaussian Processes
• A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow
• MatchingGAN: Matching-based Few-shot Image Generation
• SimEx: Express Prediction of Inter-dataset Similarity by a Fleet of Autoencoders
• Efficient and Less Centralized Federated Learning
• Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning
• Artificial Liver Classifier: A New Alternative to Conventional Machine Learning Models
• Convex Programming Based Spectral Clustering
• Towards Principled Uncertainty Estimation for Deep Neural Networks
• DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
• Adaptive Image Stream Classification via Convolutional Neural Network with Intrinsic Similarity Metrics
• Application of Quantum Pre-Processing Filter for Binary Image Classification with Small Samples
• F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
• One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
• Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
• Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
• A Deep Learning Framework for Lifelong Machine Learning
• You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries
• Effectiveness of Optimization Algorithms in Deep Image Classification
• Learning Translation Invariance in CNNs
• Closed-Loop Memory GAN for Continual Learning
• Information Condensing Active Learning
• Representation of Federated Learning via Worst-Case Robust Optimization Theory
• Large-Scale Semi-Supervised Learning via Graph Structure Learning over High-Dense Points
• Inherent Weight Normalization in Stochastic Neural Networks
• Verification of Neural Networks: Specifying Global Robustness using Generative Models
• Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation
• Bespoke vs. Prêt-à-Porter Lottery Tickets: Exploiting Mask Similarity for Trainable Sub-Network Finding
• Estimating informativeness of samples with Smooth Unique Information
• Reward-Based 1-bit Compressed Federated Distillation on Blockchain
• Schrödinger's Camera: First Steps Towards a Quantum-Based Privacy Preserving Camera
• Meta-Learning Bidirectional Update Rules
• Design space exploration of Ferroelectric FET based Processing-in-Memory DNN Accelerator
• Competing Neural Networks for Robust Control of Nonlinear Systems
• Diminishing the Effect of Adversarial Perturbations via Refining Feature Representation
• Limited Gradient Descent: Learning With Noisy Labels
• Scaled Simplex Representation for Subspace Clustering
• ADDS: Adaptive Differentiable Sampling for Robust Multi-Party Learning
• The Compact Support Neural Network
• DeepConsensus: using the consensus of features from multiple layers to attain robust image classification
• Instance-based Deep Transfer Learning
• Learning from Similarity-Confidence Data
• Robust Federated Learning by Mixture of Experts
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• Trust-Region Algorithms for Training Responses: Machine Learning Methods Using Indefinite Hessian Approximations
• Training Deep Neural Networks by optimizing over nonlocal paths in hyperparameter space
• Bifurcation Spiking Neural Network
• Learning with Collaborative Neural Network Group by Reflection
• Big Data Intelligence Using Distributed Deep Neural Networks
• Task Fingerprinting for Meta Learning in Biomedical Image Analysis
• Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design
• Improved Robustness to Open Set Inputs via Tempered Mixup
• Adversarial Learning for Zero-shot Domain Adaptation
• A Mixture of Expert Approach for Low-Cost Customization of Deep Neural Networks
• The Uncanny Similarity of Recurrence and Depth
• Bayesian Sparsification Methods for Deep Complex-valued Networks
• Consistency of Extreme Learning Machines and Regression under Non-Stationarity and Dependence for ML-Enhanced Moving Objects
• Widely Linear Kernels for Complex-Valued Kernel Activation Functions
• A Biologically Plausible Audio-Visual Integration Model for Continual Learning
• ImitAL: Learning Active Learning Strategies from Synthetic Data
• Canoe : A System for Collaborative Learning for Neural Nets
• Few-shot learning using pre-training and shots, enriched by pre-trained samples
• Max and Coincidence Neurons in Neural Networks
• CatFedAvg: Optimising Communication-efficiency and Classification Accuracy in Federated Learning
• Sequential Coordination of Deep Models for Learning Visual Arithmetic
• Smart Rewritings of the Basic Equations for Quantitative Non-Linear Inverse Scattering
• Neural Network Training with Approximate Logarithmic Computations
• Machine-learning enables Image Reconstruction and Classification in a "see-through" camera