MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression
This work improves object localization accuracy for computer vision tasks, but it is incremental as it builds on existing loss functions by adding a new geometric metric.
The paper tackles the problem of bounding box regression in object detection and instance segmentation by introducing MPDIoU, a loss function based on minimum point distance that addresses optimization issues when predicted and groundtruth boxes share the same aspect ratio but differ in width and height. Experimental results show that MPDIoU outperforms existing loss functions on models like YOLACT and YOLOv7 trained on datasets such as PASCAL VOC, MS COCO, and IIIT5k.
Bounding box regression (BBR) has been widely used in object detection and instance segmentation, which is an important step in object localization. However, most of the existing loss functions for bounding box regression cannot be optimized when the predicted box has the same aspect ratio as the groundtruth box, but the width and height values are exactly different. In order to tackle the issues mentioned above, we fully explore the geometric features of horizontal rectangle and propose a novel bounding box similarity comparison metric MPDIoU based on minimum point distance, which contains all of the relevant factors considered in the existing loss functions, namely overlapping or non-overlapping area, central points distance, and deviation of width and height, while simplifying the calculation process. On this basis, we propose a bounding box regression loss function based on MPDIoU, called LMPDIoU . Experimental results show that the MPDIoU loss function is applied to state-of-the-art instance segmentation (e.g., YOLACT) and object detection (e.g., YOLOv7) model trained on PASCAL VOC, MS COCO, and IIIT5k outperforms existing loss functions.