论文阅读--PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection

论文地址：https://arxiv.org/abs/1608.08021

算法实现：https://github.com/CharlesShang/TFFRCNN

网络设计原则： “less channels with more layers” 。

网络性能：83.8% mAP (mean average precision) on VOC2007 and
82.5% mAP on VOC2012 (2nd place), while taking only 750ms/image on Intel
i7-6700K CPU with a single core and 46ms/image on NVIDIA Titan X GPU. Theoretically,
our network requires only 12.3% of the computational cost compared
to ResNet-101, the winner on VOC2012.

算法有点：提出一个轻量级的的特征提取模型，减少计算资源的消耗，可以完成实时目标检测。


网络组件：