Scape

And could you release/explain the code for updating CAC between stages? In the released code, there exists a moving-average implementation. Which one did you use? https://github.com/RogerZhangzz/CAG_UDA/blob/b6fbea6435b2b5bc42b8043fc057878f2192dce4/models/adaptation_model.py#L529

Thanks!

> ```python > def compute_l2_distance(x, y): > N, C, H, W = x.size() > x_vec = x.view(N, C, -1) > y_vec = y.view(N, C, -1) > x_s = torch.sum(x_vec **...

@JingWang18 , actually, in the paper, the updated and upadating L2 feature norm is for the same training examples in the current iteration. So, the author's implemtentation fits the paper’s...