Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
This work addresses a key bottleneck in object detection for computer vision researchers and practitioners, offering incremental improvements over existing IoU-based losses.
The paper tackles the problem of slow convergence and inaccurate regression in bounding box regression for object detection by proposing Distance-IoU (DIoU) and Complete IoU (CIoU) losses, which incorporate normalized distance and geometric factors, resulting in faster training and notable performance gains when integrated into state-of-the-art algorithms like YOLO v3, SSD, and Faster RCNN.
Bounding box regression is the crucial step in object detection. In existing methods, while $\ell_n$-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recently, IoU loss and generalized IoU (GIoU) loss have been proposed to benefit the IoU metric, but still suffer from the problems of slow convergence and inaccurate regression. In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training than IoU and GIoU losses. Furthermore, this paper summarizes three geometric factors in bounding box regression, \ie, overlap area, central point distance and aspect ratio, based on which a Complete IoU (CIoU) loss is proposed, thereby leading to faster convergence and better performance. By incorporating DIoU and CIoU losses into state-of-the-art object detection algorithms, e.g., YOLO v3, SSD and Faster RCNN, we achieve notable performance gains in terms of not only IoU metric but also GIoU metric. Moreover, DIoU can be easily adopted into non-maximum suppression (NMS) to act as the criterion, further boosting performance improvement. The source code and trained models are available at https://github.com/Zzh-tju/DIoU.