Skip to main content

Table 7 Comparison between the chalkiness segmentation results of the weakly supervised approaches Grad-CAM, Grad-CAM++ and Score CAM with ResNet-101 as backbone on polished rice

From: Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature

Approach GT-known Loc. Acc. (%) Loc. Acc. (%) Avg. IoU (%) Layer T (%)
Grad-CAM 84.43 84.13 68.11 layer2_0_conv2 60
Grad-CAM++ 48.19 48.19 43.98 layer2_0_conv2 60
Score-CAM 68.07 66.87 55.02 layer2_2_conv3 60
  1. Only 166 chalky seed images in the polished test set were used for chalkiness segmentation evaluation. Performance is reported using the following metrics: Ground-Truth Localization Accuracy (GT-known Loc. Acc.), which represents the fraction of ground-truth chalky seed images with \(\text{ IoU } \ge 0.5\); Localization Accuracy (Loc. Acc.), which represents the fraction of ground-truth chalky images, with \(\text{ IoU } \ge 0.5\), correctly predicted by the model; Average IoU (Avg. IoU), which represents the average IoU for the set of chalky seed images. To calculate the IoU, the mask of the predicted chalkiness is obtained using a threshold \(T=60\%\) of the maximum pixel intensity. The last two columns show the layer that was used for generating the heatmap and the threshold used to binarize the heatmap when calculating IoU, respectively