YOLOv5 is a high-performance real-time object detector that plays an important role in one-stage detectors. However, there are two problems with the design of the YOLOv5 head. The common branch of classification task and regression task of the YOLOv5 head will hurt the training process, and the correlation between classification score and localization accuracy is low. We propose a Double IoU-aware Decoupled Head (DDH) and apply it to YOLOv5. The improved model is named DDH-YOLOv5, which substantially improves the localization accuracy of the model without significantly increasing FLOPS and parameters. Extensive experiments on dataset PASCAL VOC2007 show that DDH-YOLOv5 has good performance. Compared with YOLOv5, DDH-YOLOv5m and DDH-YOLOv5l proposed in this paper achieve 2.4\(\%\) and 1.3\(\%\) improvement in Average Precision (AP), respectively. Compared with Deformable DETR, which is known for its fast-converging, DDH-YOLOv5 completely outperforms Deformable DETR on COCO2017 Val with half of FLOPS and only a quarter of epochs.

YOLOv5 是一种高性能的实时目标检测器，在单级检测器中发挥着重要作用。但是，YOLOv5 头部的设计存在两个问题。YOLOv5 head 的分类任务和回归任务的共同分支会伤害训练过程，并且分类分数和定位准确率之间的相关性较低。我们提出了一个双 IoU 感知解耦头（DDH）并将其应用于 YOLOv5。改进后的模型命名为 DDH-YOLOv5，在不显着增加 FLOPS 和参数的情况下，大幅提升了模型的定位精度。在 PASCAL VOC2007 数据集上的大量实验表明，DDH-YOLOv5 具有良好的性能。与YOLOv5相比，本文提出的DDH-YOLOv5m和DDH-YOLOv5l分别达到了2.4 \(\%\)和1.3 \(\%\)分别提高了平均精度（AP）。与以快速收敛着称的 Deformable DETR 相比，DDH-YOLOv5 在 COCO2017 Val 上的表现完全优于 Deformable DETR，只有一半的 FLOPS 和四分之一的 epoch。