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

Table 3

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

Model	Original data (no aug.) (%)
VGG-16	90.6
VGG-19	91.8
ResNet-18	91.1
ResNet-50	92.7
DenseNet-121	93.9
DenseNet-169	94.4