问题
I have started working on the Object Detection. After reading several papers related to object detection. I have concluded the main steps for the training and testing.
Training: Image -> Object proposals -> Checking each proposal with GT IoU > 0.5 -> Feature extraction -> Train classifier.
Testing: Test Image -> Object proposals -> Feature extraction -> Check with Train classifier.
IoU: Intersection of Union
GT: Ground truth
Q1: Please correct me if I have mistake in understand training and testing steps
For the Object proposals, researchers are commonly using Selective Search and Edgebox methods and now after Faster RCNN many researchers are using Object proposals extraction using deep learning.
Q2: I want to know that the Selective Search and Edge box are unsupervised method for extracting proposals? whereas the deep learning methods are supervised?
Q3: Lastly, Why we need to check each extracted proposal with GT?
来源：https://stackoverflow.com/questions/40776031/queries-for-object-detection