Detail of the localization evaluation

[zwei-lin]

Hi,

Thanks for the great work. I have one question about the localization evaluation results of table 3. in the paper.

Assume the image is x, the patch operation(splits the whole image into M patches) is P( . ) and the encoder is f( . ), which one of the feature patches f(P(x)) or P(f(x)) is the feature that we used to evaluate the localization?

Thanks!