Fast R-CNN 论文 笔记 及 源码解读

Fast R-CNN

与RCNN SPPnet对比

1. RCNN首先finetune，使用log loss。然后，使用SVMs来训练，最后，使用bounding-box regressor。
2. 代价大
3. 慢

Fast R-CNN 模型结构和训练

一张图片首先经过几个卷积层和池化层产生特征向量，然后 for each object proposal a region of interest(RoI) pooling layer extracts a fixed-length feature vector from the feature map.

然后输入一组fully connected层，最终 branch into two sibling output layers:
1. one that produces softmax probability estimates over K object classes plus a catch-all “background” class
2. another layer that outputs four real-valued numbers for each of the K object classes. Each set of 4 values encodes refined bounding-box