exp_reweight = exp_reweight / np.sum(exp_reweight) * num_foreground

[Liu-wanbing]

Dear author, I have some questions about the code and paper:

1. 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.
2. 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?

[tonysy]

Hi,

1. 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.
2. 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.

Thanks.

[Liu-wanbing]

Thanks for your reply!!