- UnitBox An Advanced Object Detection Network，arxiv 16.08

最新推荐文章于 2024-06-07 15:12:44 发布

_menglan_Zi

最新推荐文章于 2024-06-07 15:12:44 发布

阅读量5.7k

点赞数 4

分类专栏： Deep Learning cvpr 文章标签： face detection FCN IoU loss

本文链接：https://blog.csdn.net/zimenglan_sysu/article/details/52225324

版权

UnitBox是一种先进的目标检测网络，通过全卷积网络架构预测对象边界和像素级分类得分，并引入IoU损失函数，直接优化预测框与真实框的最大重叠，解决传统损失函数存在的问题。相较于Faster R-CNN和DenseBox，UnitBox能更准确地预测边界，适应不同形状和尺度的对象，并且训练收敛速度快。

摘要由CSDN通过智能技术生成

- UnitBox An Advanced Object Detection Network，arxiv 16.08 （download）

该论文提出了一种新的loss function：IoU loss。这点比较有意思，也容易复现。

======

论文分析了faster-rcnn和densebox的优缺点：

1 faster-rcnn：rpn用来predict the bounding boxes of object candidates from anchors，但是这些anchors是事先定义好的（如3 scales & 3 aspect ratios），RPN shows difficult to handle the object candidates with large shape variations, especially for small objects. 也就是RPN不能很好cover所有的情况（以至于很多基于faster-rcnn的论文都在改善这点）

2 densebox：utilizes every pixel of the feature map to regress a 4-D distance vector (the distances between the current pixel and the four bounds of object candidate containing it). However, DenseBox optimizes the four-side distances as four independent variables, under the simplistic lL2 loss,；besides, to balance the bounding boxes with varied scales, DenseBox requires the training image patches to be resized to a fixed scale. As a consequence, DenseBox has to perform detection on image pyramids, which unavoidably affects the eciency of the framework.

=====