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.
@inproceedings{ren2015faster,
title={Faster r-cnn: Towards real-time object detection with region proposal networks},
author={Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian},
booktitle={Advances in neural information processing systems},
year={2015}
}| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | AR1000 | Config | Download |
|---|---|---|---|---|---|---|---|
| R-50-FPN | caffe | 1x | 3.5 | 22.6 | 58.7 | config | model | log |
| R-50-FPN | pytorch | 1x | 3.8 | 22.3 | 58.2 | config | model | log |
| R-50-FPN | pytorch | 2x | - | - | 58.6 | config | model | log |
| R-101-FPN | caffe | 1x | 5.4 | 17.3 | 60.0 | config | model | log |
| R-101-FPN | pytorch | 1x | 5.8 | 16.5 | 59.7 | config | model | log |
| R-101-FPN | pytorch | 2x | - | - | 60.2 | config | model | log |
| X-101-32x4d-FPN | pytorch | 1x | 7.0 | 13.0 | 60.6 | config | model | log |
| X-101-32x4d-FPN | pytorch | 2x | - | - | 61.1 | config | model | log |
| X-101-64x4d-FPN | pytorch | 1x | 10.1 | 9.1 | 61.0 | config | model | log |
| X-101-64x4d-FPN | pytorch | 2x | - | - | 61.5 | config | model | log |