Skip to main content

Table 1 Results of ArsenicNet method (based on V2-ResNet-101)

From: Pseudo high-frequency boosts the generalization of a convolutional neural network for cassava disease detection

Method

Accuracy (%)

Recall (%)

Precision (%)

F1-Score (%)

ArsenicNet-3

\(95.55\)

\(95.52\)

\(95.59\)

\(95.56\)

ArsenicNet-1

\(95.03\)

\(94.97\)

\(95.06\)

\(95.01\)

ArsenicNet-2

\(95.43\)

\(95.40\)

\(95.47\)

\(95.44\)

ArsenicNet-4

\(95.36\)

\(95.34\)

\(94.95\)

\(94.91\)

  1. The suffix number of ArsenicNet is the number of Arsenic blocks in the neural network which are only conducted before down-sampling
Back to article page

Plant Methods

ISSN: 1746-4811