[论文阅读]：Improving Object Detection With One Line of Code

soft nms

在目标检测中，非极大值抑制是重要的组成部分，然而它存在一个问题：他会把相邻的边界框iou大于一定阈值的直接置成0，所以可能会导致丢框现象出现，会降低评测指标。论文提出的方法，是会降低和M iou大于一定阈值的score，还是会在rank list里，并不是直接删除

A major issue with non-maxinmum suppresion is that it sets the score for neighboring detections to zero.Thus,if an object was actually presnet in that overlap threshold,it would be missed and this would lead to a drop in average precision.However,if we lower the detection scores as a function of its overlap with M,it would still be in the ranked list,although with a lower confidence.We show an illustration of the problem in Fig1.

原始nms公式

soft nms公式

这个公式是不连续的，所以提出了下面这个公式

实验结果

论文里，设置Nt是0.3，$\sigma$设置成0.5.在coco数据集上，R-FCN和Faster RCNN分别提升了1.3%和1%。在Pascal voc 07数据集上，Faster RCNN和RFCN都提升了1.7%,但是对于SSD和Yolo v2只提升了0.5,这是因为sofnms建立在高召回的基础上
softnms对与重叠物体具有很好的适应性，就像fig 1所示那样，论文也提到对于斑马，大象等性能提升很大，而对于烤面包机，吹风机提升很小，因为他们不太可能在同一图像中出现多次