Table 4 Test result that are obtained by various CNN model on CVPPP Dataset (Test set size = 160 images).
From: A CNN-based model to count the leaves of rosette plants (LC-Net)
Models | Test loss \((\times 10^{-3})\) | Test accuracy (%) | IoU | Dice score |
|---|---|---|---|---|
DeepLab V3+ | 23.7 | 97.21 | 85.11 | 91.79 |
SegNet | 19.7 | 97.92 | 86.04 | 92.50 |
Fast FCN with PSP | 21.1 | 97.57 | 85.94 | 91.54 |
U-Net | 59.8 | 96.92 | 81.55 | 89.23 |
Refine Net | 24.2 | 97.06 | 84.50 | 91.20 |
