Improved Classification of White Blood Cells with the Generative Adversarial Network and Deep Convolutional Neural Network

Table 6

10-fold cross-validation accuracy of the DNN models initialized using pretrained weights.

Model	Trans_aug1 (100 inst./class) (%)	Trans_aug2 (150 inst./class) (%)	Trans_aug3 (200 inst./class) (%)
VGG-16	91.4	91.8	92.5
VGG-19	92.9	93.6	94.4
ResNet-18	91.2	92.2	92.8
ResNet-50	94.1	94.8	95.5
DenseNet-121	95.2	95.7	96.4
DenseNet-169	95.8	96.4	96.9