how do you extract the feature of the whole image by Faster-RCNN?

Open lowoodz opened this issue 5 years ago • 2 comments

Hi, @jiasenlu jiasenlu, I am new to object recognition, I have read your paper and, it's mentioned that you have used whole image as a box and extracted its feature by Faster-RCNN. How do you achieve that? The RPN and Fast-RCNN are built into one caffe net model, do you use a customized Faster-RCNN? Can anyone help?

Mar 25 '20 06:03 lowoodz

Hi, I think I just average all the bounding box features to get the holistic image feature.

May 29 '20 04:05 jiasenlu

Thanks！

Regards Guanlin On 05/29/2020 12:30, Jiasen Lu wrote:

Hi, I think I just average all the bounding box features to get the holistic image feature.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

Jun 02 '20 06:06 lowoodz