From: Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection
Indicator
ArsenicNet
ArsenicNetPlus
Accuracy
\(95.82\%\)
\(96.27\%\)
Recall
\(95.80\%\)
\(96.25\%\)
Precision
\(95.87\%\)
\(96.30\%\)
Loss
1.721
1.360
F1-score
\(95.83\%\)