Image Classification On Emnist Letters
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| OptConv+Log+Perc | 93.65 | Efficient Neural Vision Systems Based on Convolutional Image Acquisition | - |
| Linear Classifier | 55.78 | EMNIST: an extension of MNIST to handwritten letters | - |
| VGG-5 | 95.86 | SpinalNet: Deep Neural Network with Gradual Input | - |
| MIX-ENT + VGG-5 | 95.928 | Regularizing cross entropy loss via minimum entropy and K-L divergence | - |
| µ2Net+ (ViT-L/16) | 95.03 | A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems | - |
| DWT-DCT + SVM | 89.51 | Handwritten digit and letter recognition using hybrid dwt-dct with knn and svm classifier | - |
| OPIUM Classifier | 85.27 | EMNIST: an extension of MNIST to handwritten letters | - |
| WaveMixLite-112/16 | 95.96 | WaveMix: A Resource-efficient Neural Network for Image Analysis | - |
| TextCaps | 95.39 | TextCaps : Handwritten Character Recognition with Very Small Datasets | - |
| VGG-5(Spinal FC) | 95.88 | SpinalNet: Deep Neural Network with Gradual Input | - |
| MIN-ENT + VGG-5 | 95.933 | Regularizing cross entropy loss via minimum entropy and K-L divergence | - |
0 of 11 row(s) selected.