search

chenyuntc / simple-faster-rcnn-pytorch

A simplified implemention of Faster R-CNN that replicate performance from origin paper
Other
3.99k stars 1.14k forks source link

Why should we use two localization outputs? #117

Open qjadud1994 opened 5 years ago

qjadud1994 commented 5 years ago

Hi, I have a question about structure of Faster R-CNN.

Why should we use two localization outputs from RPN and Classification Head?

I think only localization results from RPN is enough.

Can we proceed with class-specific classification only for positive boxes from RPN and just using that positive boxes coordinates for localization?

I'm so confused.

If anyone knows the answer, Please let me know.

hushunda commented 5 years ago

That like boosting

chrisway613 commented 4 years ago

yep, if u only want to get the detected object, RPN is enough. But, in order to get the more precise results, it should combine with the detection head.