Jonathan Hui
Aug 31, 2018 · 1 min read

The official reason coming from the paper is :

“Our method introduces small extra cost by the extra layers in the FPN, but has a lighter weight head. Overall our system is faster than the ResNet-based Faster R-CNN counterpart”

But there are always other reasons that caused by the implementation details. What FPN paper wants to demonstrate is that those extra layers does not hurt in practice.

    Jonathan Hui

    Written by

    Deep Learning