Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

贾伟中科院合肥

http://arxiv.org/abs/1506.01497

Computer Science > Computer Vision and Pattern Recognition
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick, Jian Sun
(Submitted on 4 Jun 2015)

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully-convolutional network that simultaneously predicts object bounds and objectness scores at each position. RPNs are trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. With a simple alternating optimization, RPN and Fast R-CNN can be trained to share convolutional features. For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007 (73.2% mAP) and 2012 (70.4% mAP) using 300 proposals per image. The code will be released.

[size=12.960000038147px]

Comments:	Technical report
Subjects:	Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:1506.01497 [cs.CV]
	(or arXiv:1506.01497v1 [cs.CV] for this version)

[size=12.960000038147px]Submission historyFrom: Kaiming He [view email]
[v1] Thu, 4 Jun 2015 07:58:34 GMT (2095kb,D)