You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on May 28, 2024. It is now read-only.
Hi, I'm confused with the (supervised) RPN loss function used in your paper (equation 3). It looks like there is no penalty for an anchor box being positive when there isn't an object. Take e.g. the extreme case of an image with no groundtruth objects in it, then there is no penalty for an anchor having high p_i.
Contrast this with the loss in the Faster RCNN paper which does impose a penalty in this case.
The text was updated successfully, but these errors were encountered:
Hi, I'm confused with the (supervised) RPN loss function used in your paper (equation 3). It looks like there is no penalty for an anchor box being positive when there isn't an object. Take e.g. the extreme case of an image with no groundtruth objects in it, then there is no penalty for an anchor having high p_i.
Contrast this with the loss in the Faster RCNN paper which does impose a penalty in this case.
The text was updated successfully, but these errors were encountered: