Dear author, I have some questions about the code and paper:
exp_reweight = exp_reweight / np.sum(exp_reweight) * num_foreground
Why "exp_reweight" is multiplied by the coefficient "num_foreground"? It is not mentioned in the paper.
Is "K" in the empirical class frequencies r = [r1, · · · , rK] on the training set in the paper the same as the class number C of the training set?
num_foreground is used to maintain the total loss coefficient same with the no-reweight setting. It's a common operation in reweight-based methods.
exp_reweight is the class frequencies in the training set. I will upload the class frequency files, or you can calculate based on the annotation of the training set.
Dear author, I have some questions about the code and paper:
exp_reweight = exp_reweight / np.sum(exp_reweight) * num_foreground
Why "exp_reweight" is multiplied by the coefficient "num_foreground"? It is not mentioned in the paper.