Closed Elody-07 closed 4 years ago
Hi, thanks for sharing your brilliant work. I noticed that when computing Sd, the two formulations are all close to 1 ( the first line when S ~= 1, Sd ~= 0.9, the second line when S ~= 0.01, Sd ~= 0.97). How does Sd balance easy and hard samples?
Hi @Elody-07, I guess you have already figured it out. In your case, it is the scaling factor term that compresses the easy foreground and background.
Hi, thanks for sharing your brilliant work. I noticed that when computing Sd, the two formulations are all close to 1 ( the first line when S ~= 1, Sd ~= 0.9, the second line when S ~= 0.01, Sd ~= 0.97). How does Sd balance easy and hard samples?