Image Classification On Gashissdb
Métriques
Accuracy
F1-Score
Precision
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | F1-Score | Precision | Paper Title | Repository |
|---|---|---|---|---|---|
| EfficientNet-b0 | 98.11 | 99.01 | 99.94 | EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks | |
| CoAtNet-1 | 98.74 | 99.38 | 99.97 | CoAtNet: Marrying Convolution and Attention for All Data Sizes | |
| ResNet-18 | 98.47 | 99.19 | 99.94 | Deep Residual Learning for Image Recognition | |
| ResNet-50 | 98.56 | 99.24 | 99.94 | Deep Residual Learning for Image Recognition | |
| ResNeXt-50-32x4d | 98.59 | 99.25 | 99.94 | Aggregated Residual Transformations for Deep Neural Networks | |
| DenseNet-169 | 96.90 | 98.38 | 99.91 | Densely Connected Convolutional Networks | |
| RegNetY-3.2GF | 97.48 | 98.70 | 99.97 | RegNet: Self-Regulated Network for Image Classification | |
| Res2Net-50 | 98.68 | 99.29 | 99.91 | Res2Net: A New Multi-scale Backbone Architecture |
0 of 8 row(s) selected.