2021-08-20 论文：目标检测

one-stage

1、RetinaNet 1708.

Kaiming He, Focal Loss for Dense Object Detection.

1）focal loss

为解决1-stage训练时正负例不平衡现象，对CE损失函数添加权重因子:
balanced cross entropy：从样本分布角度添加
focal loss：从样本分类难易程度出发添加（使loss聚焦于难分样本）

two-stage

1、Faster R-CNN 1506.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.
1506.01497
[paper]

• $rpn\_loss$：

其中，
    $i$：某个minibatch中，第$i$个anchor
    $p_i$：二分类的预测值                 $p_i^{\ast }$：gt { 1 I o U ( g t , a n c h o r ) > 0.7 0 I o U ( g t , a n c h o r ) < 0.3 \begin{cases}1 &IoU(gt,anchor)>0.7 \\ 0 &IoU(gt,anchor)<0.3\end{cases}