What does the Region Proposal Network output in Faster-RCNNs?
Does it output corrections and offsets to the anchor boxes(that were generated by using some specific aspect ratios and scales)?
Also if this the answer is YES, Suppose I have 3 scales - [8,16,32] and 3 aspect ratios - [0.5,1,2]. How is it trained to make sure that the first 4 outputs of the box regression layer(assuming the output is WH9*4) refers to the offsets/corrections of the anchor box with scale - 3 and aspect ratio 0.5?
Topic faster-rcnn object-detection cnn computer-vision
Category Data Science