OriNet about affnet HOT 4 CLOSED

About the Table 2, I would like to ask a few questions.

1. How do you train separately in the setting (1) ?
2. In the setting (2), why don't you compare the biases init 0?

from affnet.

OriNet actually is not interesting to me by itself, because it has results similar to Yi et.al, 2015. You can seen from bottom part of Table 1 that all the variants of OriNet perform essentially the same.

And it is used for Table 2, "separately" column.
Separately means that I have trained OriNet with https://github.com/ducha-aiki/affnet/blob/master/train_OriNet_test_on_graffity.py and AffNet with https://github.com/ducha-aiki/affnet/blob/master/train_AffNet_test_on_graffity.py

And combined them only in full pipeline (detection - affine - ori - desc) in test time.

In the setting (2), why don't you compare the biases init 0?

Because it failed in (1), so I thought that it is not worth it. But probably you are right and I should have try to train it anyway

from affnet.

But the parameter in setting (1,2) include ori information. How can you train "A" and keep the ori unchanged?

from affnet.

By applying https://github.com/ducha-aiki/affnet/blob/master/LAF.py#L279 transformation. It cancels the rotation

from affnet.