Instead of predicting 5 arbitrary boundary boxes, we predict offsets to each of the anchor boxes above. If we constrain the offset values, we can maintain the diversity of the predictions and have each prediction focuses on a specific shape. So the initial training will be more stable.Real-time Object Detection with YOLO, YOLOv2 and now YOLOv37K68Jonathan HuibenFollowSep 6, 2018 · 1 min readCould you help differentiating these terms: boundary box, offsets, anchor box (priors)?