| Paper | Code | Accuracy | Precision | F1-Score | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| CoAtNet: Marrying Convolution and Attention for All Data Sizes | ✓ Link | 98.74 | 99.97 | 99.38 | CoAtNet-1 | 2021-06-09 |
| Res2Net: A New Multi-scale Backbone Architecture | ✓ Link | 98.68 | 99.91 | 99.29 | Res2Net-50 | 2019-04-02 |
| Aggregated Residual Transformations for Deep Neural Networks | ✓ Link | 98.59 | 99.94 | 99.25 | ResNeXt-50-32x4d | 2016-11-16 |
| Deep Residual Learning for Image Recognition | ✓ Link | 98.56 | 99.94 | 99.24 | ResNet-50 | 2015-12-10 |
| Deep Residual Learning for Image Recognition | ✓ Link | 98.47 | 99.94 | 99.19 | ResNet-18 | 2015-12-10 |
| EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks | ✓ Link | 98.11 | 99.94 | 99.01 | EfficientNet-b0 | 2019-05-28 |
| RegNet: Self-Regulated Network for Image Classification | ✓ Link | 97.48 | 99.97 | 98.70 | RegNetY-3.2GF | 2021-01-03 |
| Densely Connected Convolutional Networks | ✓ Link | 96.90 | 99.91 | 98.38 | DenseNet-169 | 2016-08-25 |