Medical Image Classification On Nct Crc He
Métriques
Accuracy (%)
F1-Score
Precision
Specificity
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy (%) | F1-Score | Precision | Specificity | Paper Title | Repository |
|---|---|---|---|---|---|---|
| ResNet-18 | 92.66 | 95.23 | 99.90 | 99.08 | Deep Residual Learning for Image Recognition | |
| Efficientnet-b0 | 95.59 | 97.48 | 99.89 | 99.45 | EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks | |
| ResNet-50 | 94.72 | 97.09 | 100.00 | 99.34 | Deep Residual Learning for Image Recognition | |
| Res2Net-50 | 93.37 | 96.25 | 99.93 | 99.17 | Res2Net: A New Multi-scale Backbone Architecture | |
| RegNetY-3.2GF | 95.42 | 97.39 | 99.97 | 99.43 | RegNet: Self-Regulated Network for Image Classification | |
| DenseNet-169 | 94.41 | 96.90 | 99.87 | 99.30 | Densely Connected Convolutional Networks | |
| ResNeXt-50-32x4d | 95.46 | 97.46 | 99.91 | 99.43 | ResNet strikes back: An improved training procedure in timm |
0 of 7 row(s) selected.