候选区域如何生成
These proposals can be generated by some heuristics search,selective search, or by a region proposal network (RPN).
那么RPN有哪些优点呢?
RPN的优点
1.服务于整体的检测网络,使整个网络统一、简单、实现端到端训练。
Faster R-CNN is a single, unified network for object detection. The RPN module serves as the ‘attention’ of this unified network.
2.多尺度锚框作为回归参考
As shown in Figure 1, there have been two popular ways for multi-scale predictions. The first way is based on image/feature pyramids, e.g., in DPM[*] and CNN-based methods. The images are resized at multiple scales, and feature maps are computed for each scale(Figure 1(a)). This way is often useful but is time-consuming.
The second way is to use sliding windows of multiple scales(or aspect ratios) on the feature maps. If this way is used to address multiple scales, it can be thought of as a “pyramid of filters”(Figure 1(b)). The second way is usually adopted joint