Questions about the equation in the paper

[JixiangGao]

Thanks for your great work and contribution. I have some questions about the equation in the paper.

1. As section 4.3 described (the line behind the equation f(v_i^k)=... ), v_i^{(1)}=pi (Nsl / Nsmin). I'm wondering if the authors made some mistakes. It should be v_i^{(1)}=pi (Nsmin / Nsl)?

2. As described in section 4.3, Since the whole dataset is long-tailed, while we select samples from easy to hard, we also wish to select as uniform as possible across all subsets at the beginning of the training, and gradually add more hard samples as the epoch increases. In other words, at the first epoch we wish to select all the samples in the subset with lowest shots Smin (i.e. classes in Smin have the smallest number of samples) and same amount of samples in other subsets, and gradually add more samples until all the samples in all subsets are selected in the last epoch. From the equation f(v_i^k)=..., I don't understand how the hard samples and the easy samples in the same subset can be weighted in different ways in the previous and later epoch. In other words, at the 1st epoch, the easy samples have larger weights than the hard samples in the same subset. However, at the E_th epoch, the easy samples also have larger weights than the hard samples. So, I'm confused about how to implement the idea of "gradually add more hard samples as the epoch increases" as described in the paper.

[JixiangGao]

A few additions to the second question. Undeniably, with the increase of epoch, the loss weights (v_i^k) of hard samples increase. However, the loss weights of the easy samples are also increasing. So, I'm confused about how the equation f implements the idea of "gradually add more hard samples as the epoch increases".