What do the bbox_pred and bbox_targets mean?

[JoyHuYY1412]

What do the bbox_pred and bbox_targets mean?

https://github.com/yihui-he/KL-Loss/blob/0a5617f02b5c0ebc57ddedffeb212859f1b3f008/detectron/modeling/fast_rcnn_heads.py#L114

In original bbox regression, the smooth L1 loss is calculated between the offsets, but according to your paper, I think here the 'bbox_pred' is the xyxy coordinates after regression? Can you explain it?

[Ethan He]

they are still offsets. predicting xyxy are just the same as predicting xy in xywh setting