Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
复制标题
DOI：
10.1109/tpami.2016.2577031
复制
发表时间：
2017-06-01
影响因子：
23.6
通讯作者：
Sun, Jian
中科院分区：
文献类型：
--
作者：
Ren, Shaoqing;He, Kaiming;Sun, Jian
最先进的目标检测网络依赖于区域建议算法来假设目标位置。SPPnet[7]和Fast R-CNN[5]等技术的进步减少了这些检测网络的运行时间，使区域提议计算成为瓶颈。在这项工作中，我们引入了一个区域建议网络（RPN），它与检测网络共享全图像卷积特征，从而实现几乎无成本的区域建议。RPN是一个全卷积网络，它可以同时预测物体边界和物体在每个位置的得分。rpn被端到端训练以生成高质量的区域建议，这些建议被Fast R-CNN用于检测。通过简单的交替优化，RPN和Fast R-CNN可以被训练成共享卷积特征。对于非常深的VGG-16模型[19]，我们的检测系统在GPU上的帧率为5fps（包括所有步骤），同时在PASCAL VOC 2007 （73.2% mAP）和2012 （70.4% mAP）上实现了最先进的目标检测精度，每张图像使用300个提案。代码可从https://github获得。com/ShaoqingRen/faster_ rcnn。最先进的目标检测网络依赖于区域建议算法来假设目标位置。SPPnet[1]和Fast R-CNN[2]等技术的进步减少了这些检测网络的运行时间，使区域提议计算成为瓶颈。在这项工作中，我们引入了一个区域建议网络（RPN），它与检测网络共享全图像卷积特征，从而实现几乎无成本的区域建议。RPN是一个全卷积网络，它同时预测物体边界和物体在每个位置的得分。RPN经过端到端训练，生成高质量的区域建议，用于Fast R-CNN的检测。我们进一步将RPN和Fast R-CNN合并为一个网络，通过共享它们的卷积特征——使用最近流行的神经网络术语“注意”机制，RPN组件告诉统一网络去哪里看。对于非常深的VGG-16模型[3]，我们的检测系统在GPU上的帧率为5 fps（包括所有步骤），同时在PASCAL VOC 2007年，2012年和MS COCO数据集上实现了最先进的目标检测精度，每张图像只有300个建议。在ILSVRC和COCO 2015比赛中，Faster R-CNN和RPN是多个赛道第一名获奖作品的基础。代码已公开提供。
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [7] and Fast R-CNN [5] 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 highquality 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 [19], 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. Code is available at https://github. com/ShaoqingRen/faster_ rcnn.State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] 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 [3], our detection system has a frame rate of 5 fps (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.