YOLO v2
Joseph Redmon and Ali Farhadi made various improvements to YOLO v1. The resulted model YOLO v2 became better (more accurate) and faster than Faster R-CNN and SSD. They trained a stronger model (YOLO9000) with a new method, making it capable of detecting over 9000 object categories. So, the paper title reads “YOLO9000: Better, Faster, Stronger”. This article explains what changed since YOLO v1.
