Table 2 Accuracy [and F1-Score] (in percentage) of the models used in our experiments. In both classes, D-Model performs best, followed by C-Net and lastly SVM. Also, all models performed better on 5 classes compared to 195 classes
Models | 195 classes | 5 classes |
|---|---|---|
SVM | 66.43 [61.27] | 78.74 [78.63] |
D-Model | 70.78 [66.90] | 83.09 [82.94] |
C-Net | 70.49 [66.18] | 82.78 [82.61] |