- 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.
=====