Bounding Box Regression With Uncertainty for Accurate Object Detection

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 b...

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2883 - 2892
Main Authors He, Yihui, Zhu, Chenchen, Wang, Jianren, Savvides, Marios, Zhang, Xiangyu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2019
Subjects
Categorization
Recognition: Detection
Retrieval
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2575-7075
DOI:10.1109/CVPR.2019.00300