# Why YOLO algorithm predicts B boxes for each grid cell S?

In yolo each grid cell predicts multiple bounding boxes lets say in YOLOv1 it predicts B=2, what is the advantage as it only predicts class probabilities only once for each grid cell. If that so why not only use one bounding box...

• As noted in the YOLOv1 paper: "Each predictor gets better at predicting certain sizes, aspect ratios, or classes of object, improving overall recall" $\Rightarrow$ During training, each of the Bounding boxes being predicted at the same cell. get specialized to certain shapes/ classes. – Javier TG May 13 at 17:59