作者:Ross Girshick(RBG大神)

发布时间:2015

发布期刊:ICCV

论文全称:Fast R-CNN

论文地址:https://www.semanticscholar.org/paper/Fast-R-CNN-Girshick/7ffdbc358b63378f07311e883dddacc9faeeaf4b

代码:https://github.com/rbgirshick/fast-rcnn*.*

地位:提出ROI-Poling

一、摘要

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to effificiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9× faster than R-CNN, is 213× faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3× faster, tests 10× faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at https://github.com/rbgirshick/fast-rcnn*.*

二、研究背景

而解决这些问题的策略通常会影响速度、精确性和简单性