1、论文总述

在这里插入图片描述

这篇论文提出了一个anchor-free的模块FSAF，它也有分类分支和回归分支，并分配了对应的损失函数（交叉熵和IOU损失函数），然后训练时候首先把box分配到FPN所有的level上，对box计算对应每个level的分类和损失和，这个损失和最小的即把这个box分配到FPN的这个l层上训练，即实现了Feature Selective ，这是自动筛选的，并没有像retinanet那样，根据GT与anchor的IOU或者根据FPN论文里的那个公式（如下图）来分配，
在这里插入图片描述

这个FSAF模块有点像centerNet和FCOS（下一篇博客解读这篇论文），即feature map上的每个点都预测一个框，有其对应的分类得分和回归的距离（这个距离是点到直线的距离，即该点到四条边界的距离），当然，这里的模块比较简单，例如FCOS比它了多了一个centerness-map，效果就好很多；不过论文里也说了，这个模块单独使用的话，没有one-stage的retinaNET效果好，这个模块与基于anchor的retinaNet一起训练使用，效果很好，加上多尺度训练测试啥的，在Coco上的mAP已经达到了42.8，用resnext的话44.6 ？？

注：文中有说明，这个网络算法对小目标比较友好，后面可以测试一下。

对于这篇论文，知乎上有一篇文章讲解的很好，直接转移到这即可：
[CVPR2019]:FSAF for Single-Shot Object Detection

We propose a simple and effective approach named fea
ture selective anchor-free (FSAF) module to address these
two limitations simultaneously.
Our motivation is to let
each instance select the best level of feature freely to optimize the network, so there should be no anchor boxes to
constrain the feature selection in our module. Instead, we
encode the instances in an anchor-free manner to learn the
parameters for classification and regression. The general
concept is presented in Figure 3. An anchor-free branch
is built per level of feature pyramid, independent to the
anchor-based branch. Similar to the anchor-based branch,
it consists of a classification subnet and a regression subnet (not shown in figure). An instance can be assigned to
arbitrary level of the anchor-free branch.
During training,
we dynamically select the most suitable level of feature for
each instance based on the instance content instead of just
the size of instance box. The selected level of feature then
learns to detect the assigned instances. （基于GT的内容选feature而不是GT的box大小）
At inference, the
FSAF module can run independently or jointly with anchorbased branches. Our FSAF module is agnostic to the backbone network and can be applied to single-shot detectors
with a structure of feature pyramid. Additionally, the instantiation of anchor-free branches and online feature selection can be various. In this work, we keep the implementation of our FSAF module simple so that its computational
cost is marginal compared to the whole network

2、Ground-truth和loss的设计

在这里插入图片描述
Figure 5: Supervision signals for an instance in one feature level of the anchor-free branches. We use focal loss for classification and IoU loss for box regression.