Shape-IoU: More Accurate Metric considering Bounding Box Shape and Scale

TL;DR

This paper introduces Shape IoU, a novel bounding box regression loss that emphasizes the shape and scale of bounding boxes, leading to more accurate object detection results.

Contribution

The paper proposes Shape IoU, a new loss function that considers bounding box shape and scale, improving regression accuracy over existing methods.

Findings

Improved detection performance across multiple tasks.

Outperforms existing bounding box regression methods.

Achieves state-of-the-art results in experiments.

Abstract

As an important component of the detector localization branch, bounding box regression loss plays a significant role in object detection tasks. The existing bounding box regression methods usually consider the geometric relationship between the GT box and the predicted box, and calculate the loss by using the relative position and shape of the bounding boxes, while ignoring the influence of inherent properties such as the shape and scale of the bounding boxes on bounding box regression. In order to make up for the shortcomings of existing research, this article proposes a bounding box regression method that focuses on the shape and scale of the bounding box itself. Firstly, we analyzed the regression characteristics of the bounding boxes and found that the shape and scale factors of the bounding boxes themselves will have an impact on the regression results. Based on the above conclusions, we propose the Shape IoU method, which can calculate the loss by focusing on the shape and scale of the bounding box itself, thereby making the bounding box regression more accurate. Finally, we validated our method through a large number of comparative experiments, which showed that our method can effectively improve detection performance and outperform existing methods, achieving state-of-the-art performance in different detection tasks.Code is available at https://github.com/malagoutou/Shape-IoU