MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression
Paper address: https://arxiv.org/pdf/2307.07662.pdf
Introduction to the paper
Bounding box regression (BBR) is widely used in target detection and instance segmentation and is an important step in target localization. However, most existing bounding box regression loss functions cannot be optimized when the predicted box has the same aspect ratio as the groundtruth box, but completely different width and height values. In order to solve the above problems, we fully exploited the geometric characteristics of horizontal rectangles and proposed a new bounding box similarity comparison metric MPDIoU based on the minimum point distance.
MPDIoU core design ideas
Initially,