Question about the target centers.

[wjun0830]

Thanks for the interesting paper.

I have 2 questions.

1. The first one is about the assignment process. In the paper, it says that the class centers are updated in a way of the weighted moving average.

However, if we softly assign the target center e.g., 0.9 * c1 + 0.1 * c2, isn't the property of uniformity violated? Or do you assign "c1" if the weight for c1 is 0.9?

2. How does Eq. 1 satisfy the uniformity? If the feature dimension is 2048 and there are 1000 classes, making 1000 centers orthogonal does not seem to make them uniformly distributed.

Thank you.

[whper07]

In my opinion, the relation between the relative size of the dimension and the number of categories does not seem to matter. I'm not sure