Rethink the IoU-based loss functions for bounding box regression

The ℓ_n-norm loss is widely used as the bounding box regression loss function in the existing object detectors, but Intersection over Union (IoU) is used to evaluate the accuracy of the bounding box locating. There is no inevitable correlation between low ℓ_n-norm loss and high IoU, so IoU-based loss functions represented by IoU⁺¹, Generalized IoU (GIoU), Distance IoU (DIoU) and Complete IoU (CIoU) appeared. Based on the simulation experiment of bounding box regression, we point out that the existing IoU-based loss functions have the problems of slow convergence speed, large training error, and poor training result. From the specific bounding box regression process, the causes of the problems are explored, and a new loss function LIoU combining smooth ℓ₁-norm loss and IoU is proposed. The experimental results on the two-stage object detectors Faster R-CNN, Mask R-CNN and the single-stage object detector RetinaNet consistently show that LIoU gets rid of the problems of the existing IoU-based loss functions and can further improve the performance of the object detectors. The source code and model training weights are open source on https://github.com/iamRyanChia/LIoU.https://github.com/iamRyanChia/LIoU.