Gaussian Combined Distance: A Generic Metric for Object Detection

In object detection, a well-defined similarity metric can significantly enhance the model performance. Currently, the intersection over union (IoU)-based similarity metric is the most commonly preferred choice for detectors. However, detectors using IoU as a similarity metric often perform poorly when detecting small objects because of their sensitivity to minor positional deviations. To address this issue, recent studies have proposed the Wasserstein distance (WD) as an alternative to IoU for measuring the similarity of Gaussian-distributed bounding boxes. However, we have observed that the WD lacks scale invariance, which negatively impacts the model's generalization capability. In addition, when used as a loss function, its independent optimization of the center attributes leads to slow model convergence and unsatisfactory detection precision. To address these challenges, we introduce the Gaussian Combined Distance (GCD). Through analytical examination of GCD and its gradient, we demonstrate that GCD not only possesses scale invariance but also facilitates joint optimization, which enhances model localization performance. Extensive experiments on the AI-TOD-v2 dataset for tiny object detection show that GCD, as a bounding box regression loss function and label assignment metric, achieves state-of-the-art (SOTA) performance across various detectors. We further validated the generalizability of GCD on the MS-COCO-2017 and Visdrone-2019 datasets, where it outperforms the WD across diverse scales of datasets. The code is available at: https://github.com/MArKkwanGuan/mmdet-GCD.