准确物体检测与语义分割的丰富特征层次结构

Nov, 2013

准确物体检测与语义分割的丰富特征层次结构

Rich feature hierarchies for accurate object detection and semantic segmentation

Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik

TL;DR提出一种基于卷积神经网络的Region Proposal方法R-CNN，它与CNN结合起来使用更高的上下文信息，加上有监督的预培训方法，实现了在PASCAL VOC 2012数据集上的平均准确率mAP达到53.3%。

Abstract

Can a large convolutional neural network trained for whole-image classification on ImageNet be coaxed into detecting objects in PASCAL? We show that the answer is yes, and that the resulting system is simple, scalable, and boosts mean average precision, relative to the venerable deformable part model, by more than 40% (achieving a final mAP of 48% on VOC 200