leo-p
commented
7 years ago Summary:
- Dataset: PASCAL VOC and COCO.
- Objective: Improve on Fast R-CNN and SPPnet by incorporating the region proposal network directly.
Both Fast R-CNN and SPPnet takes as input an image and several possibles objects (corresponding to regions of interest) and score each of them. They are thus two different entities:
- A region proposal network.
- A classification/detection network (Fast R-CNN/SSPnet).
Architecture:
First image features are extracted using a state of the art ConvNet, then they are used for both Region proposal and actual detection/classification on those regions.
Results:
By incorporating the region proposal network right after the feature ConvNet its computation cost becomes basically free which leads to an elegant solution (only one network) but more importantly greatly improve speed at test time.
https://arxiv.org/pdf/1506.01497v3.pdf
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.