Faster R-CNN Overview

1. What is Faster R-CNN?

Faster R-CNN?is an object detection model that improves Fast R-CNN?by utilizing a region proposal network (RPN) with the CNN model. The RPN shares full-image convolutional features with the detection network, enabling nearly cost-free region proposals. It 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 Fast R-CNN uses?for detection. RPN and Fast?R-CNN?are merged into a single network by sharing their convolutional features: the RPN component tells the unified network where to look.

As a whole, Faster R-CNN consists of two modules. The first module is a deep fully convolutional network that proposes regions, and the second module is the Fast R-CNN detector that uses the proposed regions.

2. Faster R-CNN architecture :

1. RPN: For generating region proposals.
2. Fast R-CNN: For detecting objects in the proposed regions (we discussed this topic in the last article).

3. Region Proposal Network (RPN) :

As I mentioned before, 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. RPN and algorithms like?Fast R-CNN?can be merged 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.

RPNs are designed to efficiently predict region proposals with a wide range of scales and aspect ratios. RPNs use anchor boxes that serve as references at multiple scales and aspect ratios. The scheme can be thought of as a pyramid of regression references, which avoids enumerating images or filters of multiple scales or aspect ratios.

RPN was proposed to solve the limitations of Selective Search which are offline algorithms and computationally expensive. RPN is more efficient.

If RPN needs to be summarised briefly it will be "Image passes through CNN and get feature map. For each position in the feature map, you have anchor boxes and every anchor box has two possible outcomes - foreground and background."

The main contributions of the Faster RCNN paper are :

• Proposing?region proposal network (RPN)?which is a fully convolutional network that generates proposals with various scales and aspect ratios. The RPN implements the terminology of?neural networks with attention?to telling the object detection (Fast R-CNN) where to look.
• Rather than using?pyramids of images?(i.e. multiple instances of the image but at different scales) or?pyramids of filters?(i.e. multiple filters with different sizes), this paper introduced the concept of?anchor boxes. An anchor box is a reference box of a specific scale and aspect ratio. With multiple reference anchor boxes, then multiple scales and aspect ratios exist for the single region. This can be thought of as a?pyramid of reference anchor boxes. Each region is then mapped to each reference anchor box and thus detecting objects at different scales and aspect ratios.
• The convolutional computations are shared across the RPN and the Fast R-CNN. This reduces the computational time.

Faster RCNN paper

MY GITHUB