What does DIOU stand for?

Distance Intersection over Union

DIoU stands for "Distance Intersection over Union," and it's an advanced metric used in computer vision to evaluate how well predicted bounding boxes align with ground truth boxes. Unlike the traditional IoU (Intersection over Union), which only considers the overlap area, DIoU also takes into account the distance between the centers of the two boxes. This helps improve object detection models by penalizing predictions that are far from the actual object's center, even if they partially overlap.

DIoU is especially useful in deep learning models for tasks like image recognition, autonomous driving, and facial detection, where precise localization matters. It helps neural networks learn better spatial alignment and makes training more stable. Developers and researchers often choose DIoU over standard IoU or GIoU for more accurate bounding box regression in YOLO, SSD, and other object detection architectures.