Hi, I have some questions regarding the Average Drop/Increase in Confidence metric in section 4.2.
In this experiment, rather than do point-wise multiplication with the original generated saliency map, we slightly modify by limiting the number of positive pixels in the saliency map (50% of pixels of the image are muted in our experiment).
Do you select 50% of the pixels randomly for every image?
Is it 50% of the input image, or 50% of the overlayed image produced by the multiplication?
Hi, I have some questions regarding the Average Drop/Increase in Confidence metric in section 4.2.