Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
This is an incremental improvement for computer vision researchers and practitioners in object detection, enhancing loss functions for bounding box regression.
The paper tackles bounding box regression in object detection by introducing a family of power IoU losses with a parameter α, which outperforms existing IoU-based losses, offers flexibility in accuracy, and improves robustness to small datasets and noisy bounding boxes.
Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss and its variants. In this paper, we generalize existing IoU-based losses to a new family of power IoU losses that have a power IoU term and an additional power regularization term with a single power parameter $α$. We call this new family of losses the $α$-IoU losses and analyze properties such as order preservingness and loss/gradient reweighting. Experiments on multiple object detection benchmarks and models demonstrate that $α$-IoU losses, 1) can surpass existing IoU-based losses by a noticeable performance margin; 2) offer detectors more flexibility in achieving different levels of bbox regression accuracy by modulating $α$; and 3) are more robust to small datasets and noisy bboxes.