论文题目:A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network
论文作者:Qijie Zhao , Tao Sheng ,Yongtao Wang , Zhi Tang , Ying Chen , Ling Cai and Haibin Ling
注:以下是个人解读,若有出入之处,还请指出。
Motivation:
作者在文中认为现在的目标检测网络像DSSD、RetinaNet、RefineDet等都普遍采用FPN的网络结构,但是它们的backbone都用的是目标分类的backbone,这样存在两方面局限性:
原文:
First, feature maps in the pyramid are not representative enough for the object detection task, since they are simply constructed from the layers (features) of the backbone designed for object classification task.
Second, each feature map in the pyramid (used for detecting objects in a specific range of size) is mainly or even solely constructed from single-level layers of the backbone, that is, it mainly or only contains single-level information.
1、FPN中的feature map虽然可以有助于保留更多的位置信息和语义信息,但还是不能说FPN就可以代表目标检测任务的网络结构了。因为,它只是简单的提取目