Some questions about paper

[taokong]

Some questions about paper

[taokong]

@DuinoDu
For the first question, we find that not sharing features could get better detection results. Maybe you can have try about sharing weights with four scales.
The objectness prior is modified from RPN. The original RPN will do bbox regression to get better localization, however, the anchor's location will be changed after bbox reg. So Faster R-CNN must use ROI-Pooling to extract features on these changed anchors. Thus the detection module will bring repeated computations.
@mattdingmeng @chengshuai
Yes, the idea of reverse connection is similar with DSSD, FPN and TDM. In fact, the four works are developed amost at the same period. RON and FPN are both accepted by cvpr2017.

[chengshuai]

@DuinoDu @mattdingmeng

The reverse connection is similar with the idea of the paper(the Feature Pyramid Networks for Object Detection and Deconvoluiton SSD).

[mattdingmeng]

@DuinoDu for the second comment, I agree with you. The objectness prior is very close to the rpn in faster rcnn. I think the main contribution of this paper is the reverse connection, which combine different scaled feature map to detect objects in different size.

[DuinoDu]

Thanks!

[kl456123]

I want to know why it is faster than Faster R-CNN.
Who can help me ,thanks a lot

[luuuyi]

@kl456123 the author mentioned it that use ROI-Pooling can bring extra computation. Meanwhile, I think discarding Fully Connection Layer also can accelerate the speed of train and inference.

[liuguiyangnwpu]

I want to study about the small target detection in large scale scene.
But I find that, the CNN feature Map is very important, If the CNN base model can't find the target, the regression has no meaning.
Could you give me some tips about how to advance the CNN feature model ?

[twmht]

@taokong

by the way, I have sent an email to you to ask some questions about hypernet (https://arxiv.org/abs/1604.00600). Please take a look if you have time:)