BriefGPT.xyz
May, 2015
基于多区域和语义分割感知的CNN目标检测模型
Object detection via a multi-region & semantic segmentation-aware CNN model
HTML
PDF
Spyros Gidaris, Nikos Komodakis
TL;DR
本文提出一种基于卷积神经网络和语义分割的目标检测系统，利用迭代定位机制，通过高效运用模块来检测物体，并在PASCAL VOC数据集上获得了比其他方法更高的检测精度。
Abstract
We propose an
object detection
system that relies on a multi-region deep
convolutional neural network
(CNN) that also encodes
semantic segmentati
→