Research Article
Improved Classification of White Blood Cells with the Generative Adversarial Network and Deep Convolutional Neural Network
Table 9
10-fold cross-validation accuracy of the DNN models initialized using random weights.
| Model | Tran_aug1 + GAN_aug1 (200 inst./class) (%) | Tran_aug2 + GAN_aug2 (300 inst./class) (%) | Tran_aug3 + GAN_aug3 (400 inst./class) (%) |
| VGG-16 | 92.5 | 93.2 | 93.9 | VGG-19 | 93.3 | 93.7 | 94.4 | ResNet-18 | 93.2 | 94.5 | 95.1 | ResNet-50 | 94.2 | 95.2 | 95.6 | DenseNet-121 | 95.5 | 96.1 | 97.3 | DenseNet-169 | 95.9 | 96.3 | 97.3 |
|
|