Skip to main content

Table 6 Results of our proposed method

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

Method

Accuracy (%)

Pretraining

ResNet-50 [51]

\(78.8\)

Yes

ArsenicNet-1 (Based ResNet-50)

\(83.05\)

No

ArsenicNet-2 (Based ResNet-50)

\(83.68\)

No

ArsenicNet-3 (Based ResNet-50)

\(84.70\)

No

ArsenicNet-4 (Based ResNet-50)

\(84.13\)

No

ArsenicNetPlus (Based ResNet-50)

\(86.59\)

No

Back to article page

Plant Methods

ISSN: 1746-4811