In this paper, YOLO has three features compared to YOLO v1. This question is about Better and Faster.

In the Better section, there are many techniques such as Batch Norm, Anchor Box and so on. In the Faster section, there is a darknet only. Darknet has 19 Conv Layer but it doesn't use Layer Norm or Passthrough Layer. So, I think that Darknet doesn't use Better section techniques.

Is the Better Section model different from Faster Section Model? In my understanding, there are three models named YOLO v2. First is Better YOLO v2, second is Faster YOLO v2, third Strong YOLO v2. Is this right?



You must log in to answer this question.

Browse other questions tagged .