Unified-IoU: For High-Quality Object Detection

TL;DR

Unified-IoU (UIoU) is a novel loss function for object detection that dynamically emphasizes high-quality predictions, improving accuracy especially at high IoU thresholds and balancing training speed.

Contribution

The paper introduces Unified-IoU, a new IoU loss that adaptively shifts focus to high-quality predictions, enhancing detection precision and training efficiency.

Findings

UIoU outperforms existing IoU losses at high IoU thresholds

Improves detection accuracy on multiple datasets

Balances training speed with high-precision detection

Abstract

Object detection is an important part in the field of computer vision, and the effect of object detection is directly determined by the regression accuracy of the prediction box. As the key to model training, IoU (Intersection over Union) greatly shows the difference between the current prediction box and the Ground Truth box. Subsequent researchers have continuously added more considerations to IoU, such as center distance, aspect ratio, and so on. However, there is an upper limit to just refining the geometric differences; And there is a potential connection between the new consideration index and the IoU itself, and the direct addition or subtraction between the two may lead to the problem of "over-consideration". Based on this, we propose a new IoU loss function, called Unified-IoU (UIoU), which is more concerned with the weight assignment between different quality prediction boxes. Specifically, the loss function dynamically shifts the model's attention from low-quality prediction boxes to high-quality prediction boxes in a novel way to enhance the model's detection performance on high-precision or intensive datasets and achieve a balance in training speed. Our proposed method achieves better performance on multiple datasets, especially at a high IoU threshold, UIoU has a more significant improvement effect compared with other improved IoU losses. Our code is publicly available at: https://github.com/lxj-drifter/UIOU_files.