Bounding box regression plays a crucial role in the field of object detection, and the positioning accuracy of object detection largely depends on the loss function of bounding box regression. Existing researchs improve regression performance by utilizing the geometric relationship between bounding boxes, while ignoring the impact of difficult and easy sample distribution on bounding box regression. In this article, we analyzed the impact of difficult and easy sample distribution on regression results, and then proposed Focaler-IoU, which can improve detector performance in different detection tasks by focusing on different regression samples. Finally, comparative experiments were conducted using existing advanced detectors and regression methods for different detection tasks, and the detection performance was further improved by using the method proposed in this paper.Code is available at \url{https://github.com/malagoutou/Focaler-IoU}.

翻译：边界框回归在目标检测领域中起着至关重要的作用，而目标检测的定位精度在很大程度上取决于边界框回归的损失函数。现有研究通过利用边界框之间的几何关系来提升回归性能，却忽略了困难样本与简单样本分布对边界框回归的影响。本文分析了困难样本与简单样本分布对回归结果的影响，进而提出了Focaler-IoU，该方法通过聚焦不同的回归样本，能够在不同检测任务中提升检测器性能。最后，针对不同检测任务，我们使用现有先进检测器与回归方法进行了对比实验，采用本文提出的方法进一步提升了检测性能。代码开源地址为 \url{https://github.com/malagoutou/Focaler-IoU}。