Translator Disclaimer
12 September 2020 Mixed geometric loss for bounding box regression in object detection
Author Affiliations +

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.

© 2020 SPIE and IS&T 1017-9909/2020/$28.00 © 2020 SPIE and IS&T
Xudie Ren, Fucai Luo, and Shenghong Li "Mixed geometric loss for bounding box regression in object detection," Journal of Electronic Imaging 29(5), 053005 (12 September 2020).
Received: 26 April 2020; Accepted: 17 August 2020; Published: 12 September 2020

Back to Top