# GAOC: A Gaussian Adaptive Ochiai Loss for Bounding Box Regression

## TL;DR

This paper introduces GAOC, a new loss function for object detection that improves accuracy by addressing scale and drift issues in bounding box regression.

## Contribution

The novel GAOC loss function combines the Ochiai Coefficient with a Gaussian Adaptive distribution to enhance bounding box regression.

## Key findings

- GAOC outperforms existing BBR loss functions on PASCAL VOC and MS COCO benchmarks.
- GAOC improves detection robustness and accuracy by reducing sensitivity to positional deviations.
- The method is scale-invariant and effectively addresses drift in bounding box regression.

## Abstract

Bounding box regression (BBR) loss plays a critical role in object detection within computer vision. Existing BBR loss functions are typically based on the Intersection over Union (IoU) between predicted and ground truth boxes. However, these methods neither account for the effect of predicted box scale on regression nor effectively address the drift problem inherent in BBR. To overcome these limitations, this paper introduces a novel BBR loss function, termed Gaussian Adaptive Ochiai BBR loss (GAOC), which combines the Ochiai Coefficient (OC) with a Gaussian Adaptive (GA) distribution. The OC component normalizes by the square root of the product of bounding box dimensions, ensuring scale invariance. Meanwhile, the GA distribution models the distance between the top-left and bottom-right corners (TL/BR) coordinates of predicted and ground truth boxes, enabling a similarity measure that reduces sensitivity to positional deviations. This design enhances detection robustness and accuracy. GAOC was integrated into YOLOv5 and RT-DETR and evaluated on the PASCAL VOC and MS COCO 2017 benchmarks. Experimental results demonstrate that GAOC consistently outperforms existing BBR loss functions, offering a more effective solution.