Mixed geometric loss for bounding box regression in object detection

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.