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

TL;DR

This paper introduces a Region Proposal Network (RPN) that shares features with the detection network, enabling faster, nearly real-time object detection with high accuracy on standard datasets.

Contribution

The paper presents the first fully convolutional RPN that generates high-quality region proposals efficiently and integrates seamlessly with Fast R-CNN for end-to-end training.

Findings

Achieves 5 fps detection speed with VGG-16 on GPU.

Outperforms previous methods on PASCAL VOC and MS COCO datasets.

Used in winning entries of ILSVRC and COCO competitions.

Abstract

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. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features---using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. 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, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.