# Bounding Box Regression with Uncertainty for Accurate Object Detection

Source: [Bounding Box Regression with Uncertainty for Accurate Object Detection](<https://www.sota2.com/research/paper/68fa659f1e209131cea0b52a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T02:59:55.800Z

Authors: Yihui He, Chenchen Zhu, Jianren Wang, Marios Savvides, Xiangyu Zhang

Published: 2018-09-23T07:07:01.000Z

## Abstract

Large-scale object detection datasets (e.g., MS-COCO) try to define the ground truth bounding boxes as clear as possible. However, we observe that ambiguities are still introduced when labeling the bounding boxes. In this paper, we propose a novel bounding box regression loss for learning bounding box transformation and localization variance together. Our loss greatly improves the localization accuracies of various architectures with nearly no additional computation. The learned localization variance allows us to merge neighboring bounding boxes during non-maximum suppression (NMS), which further improves the localization performance. On MS-COCO, we boost the Average Precision (AP) of VGG-16 Faster R-CNN from 23.6% to 29.1%. More importantly, for ResNet-50-FPN Mask R-CNN, our method improves the AP and AP90 by 1.8% and 6.2% respectively, which significantly outperforms previous state-of-the-art bounding box refinement methods. Our code and models are available at: github.com/yihui-he/KL-Loss

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on OGSOD](<https://www.sota2.com/research/sota/object-detection-on-ogsod.md>): Object Detection; OGSOD; mAP: 41.8.

- [Object Detection on PASCAL VOC 2007 (test)](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc-2007-test.md>): Object Detection; PASCAL VOC 2007 (test); mAP: 71.6.

- [Object Detection on MS COCO (test-dev)](<https://www.sota2.com/research/sota/object-detection-on-ms-coco-test-dev.md>): Object Detection; MS COCO (test-dev); mAP@.5: 57.8.

- [Object Detection on COCO (test-dev)](<https://www.sota2.com/research/sota/object-detection-on-coco-test-dev.md>): Object Detection; COCO (test-dev); mAP: 44.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1809.08545>)

[PDF](<https://arxiv.org/pdf/1809.08545.pdf>)

[Implementation](<https://www.sota2.com/github.com/yihui-he/KL-Loss>)