Intersection over Union with smoothing for bounding box regression
This work addresses the need for more efficient and accurate bounding box regression in object detection tasks, representing an incremental improvement over existing loss functions.
The authors tackled the problem of bounding box regression by improving the Intersection over Union (IoU) loss function to converge faster, be smooth and continuous, and achieve more precise label approximations, resulting in experimental outperformance over IoU, DIoU, CIoU, and SIoU by a large margin.
We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster, to make the surface of the loss function smooth and continuous over the whole searched space, and to reach a more precise approximation of the labels. The main principle is adding a smoothing part to the original IoU, where the smoothing part is given by a linear space with values that increases from the ground truth bounding box to the border of the input image, and thus covers the whole spatial search space. We show the motivation and formalism behind this loss function and experimentally prove that it outperforms IoU, DIoU, CIoU, and SIoU by a large margin. We experimentally show that the proposed loss function is robust with respect to the noise in the dimension of ground truth bounding boxes. The reference implementation is available at gitlab.com/irafm-ai/smoothing-iou.