Abstract
The loss function for bounding box regression (BBR) is essential to object detection. Its good definition will bring significant performance improvement to the model. Most existing works assume that the examples in the training data are high-quality and focus on strengthening the fitting ability of BBR loss. If we blindly strengthen BBR on low-quality examples, it will jeopardize localization performance. Focal-EIoU v1 was proposed to solve this problem, but due to its static focusing mechanism (FM), the potential of non-monotonic FM was not fully exploited. Based on this idea, we propose an IoU-based loss with a dynamic non-monotonic FM named Wise-IoU (WIoU). When WIoU is applied to the state-of-the-art real-time detector YOLOv7, the AP-75 on the MS-COCO dataset is improved from 53.03% to 54.50%.
Abstract (translated)
框回归损失函数(BBR)对于物体检测至关重要。一个好的定义将给模型带来显著的性能改进。大多数现有工作假设训练数据中的示例质量较高,并专注于加强BBR损失的匹配能力。如果我们盲目地加强BBR对某些质量较低的示例,它将危及定位性能。因此,我们提出了基于IoU的损失函数,名为 Wise-IoU(WIoU),该损失函数采用动态非单调FM。当WIoU应用于最先进的实时检测器YOLOv7时,MS-COCO数据集的AP-75值从53.03%提高到了54.50%。
URL
https://arxiv.org/abs/2301.10051
