Bounding-Box Regression and IoU Losses

Learn box coordinates with IoU-based losses: IoU, GIoU, DIoU and CIoU.

Advanced

$\text{IoU} = \frac{|A \cap B|}{|A \cup B|}$ . GIoU/DIoU/CIoU add penalties for non-overlapping, distant or mis-shaped boxes.

Spotted a mistake or want to add detail? Suggest an improvement — Content Contributors' edits are reviewed by editors before they go live.

Discussion (0)