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]
其中,
i i i:某个minibatch中,第 i i i个anchor
p i p_i pi:二分类的预测值 p i ∗ p_i^* pi∗: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}