Abstract. Predicting bounding box with higher intersection over union (IoU) is one of the most important issues in many computer vision tasks. The ℓn-norm loss and IoU-based loss are two conventional approaches to guide a training process in recent methods. However, the optimization direction of ℓn-norm loss is not exactly the same as maximizing the metric. In addition, IoU-based loss suffers from some inevitable disadvantages due to the direct addition of IoU. According to the shape, size, and position properties, we design a mixed geometric (MG) regression loss to increase the similarity and the overlapping area of two bounding boxes. The shape is described by the cosine similarity of diagonal vectors, the size is measured by the length or width of the boxes, and the location is calculated by the center positions of the boxes. Simulation experiments verify that the proposed MG loss can achieve competitive convergence speed and regression accuracy. By introducing the state-of-the-art models in object detection, experiments are carried out on a well-known benchmark dataset, and the results demonstrate the effectiveness of our method in object detection.

中文翻译：

---

对象检测中边界框回归的混合几何损失

摘要。预测具有更高交集比（IoU）的边界框是许多计算机视觉任务中最重要的问题之一。ℓn 范数损失和基于 IoU 的损失是在最近的方法中指导训练过程的两种传统方法。然而，ℓn-norm loss 的优化方向与最大化度量并不完全相同。此外，由于直接添加了 IoU，基于 IoU 的损失会遭受一些不可避免的缺点。根据形状、大小和位置属性，我们设计了混合几何（MG）回归损失，以增加两个边界框的相似性和重叠区域。形状用对角线向量的余弦相似度描述，大小用盒子的长或宽来衡量，位置用盒子的中心位置计算。仿真实验验证了所提出的 MG 损失可以达到具有竞争力的收敛速度和回归精度。通过在目标检测中引入最先进的模型，在众所周知的基准数据集上进行了实验，结果证明了我们的方法在目标检测中的有效性。