DliHjiang comments

Results 6 comments of


                                            DliHjiang

when distilling Faster RCNN with FPN, do we need to firstly assign gt box to different FPN level and then generate imitation region? Or for every FPN level, we generate imitation region according to all gt boxes?

I met with some problems when add your proposed imitation loss to faster rcnn with fpn, I assign gt in this way: one a certain level, for a gt box,...

when distillation with FPN，which feature map shuold we select to calculate imitation loss, feature map of FPN(P3、P4...) or feature of backbone(C3、C4...) or others?

when distilling Faster RCNN with FPN, do we need to firstly assign gt box to different FPN level and then generate imitation region? Or for every FPN level, we generate...

when distillation with FPN，which feature map shuold we select to calculate imitation loss, feature map of FPN(P3、P4...) or feature of backbone(C3、C4...) or others?

the question is how to assign gt box to different level? could you please explain in detail?

SSD

> 你可以用gluoncv去做下实验，差别很大。 > … 我想问一下您复现的Fine Grained feature imitation实验中roi Align和roi pooling效果会差多少？论文中roi Align提升约2.9%，那么如果是roi pooling大约提升多少呢？

SSD

> 看他github的 > … > ---Original--- > From: "DliHjiang" Date: Wed, Mar 18, 2020 14:51 PM > To: "twangnh/Distilling-Object-Detectors" Cc: "Author" > > > > > 你可以用gluoncv去做下实验，差别很大。 > … >...

distance threshold setting when using P3-P6 to do self-supervised learning?

Thanks very much! I will try it!