Bounding Box Regression with Uncertainty for Accurate Object Detection

2018/09/23 by Yihui He, Chenchen Zhu, He, Yihui +7 · 7 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.1809.08545

openalex publication_date 2018/09/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry\n and Semantics
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Cascade R-CNN: Delving into High Quality Object Detection
• CrowdHuman: A Benchmark for Detecting Human in a Crowd
• Learning 6-DoF Grasping and Pick-Place Using Attention Focus
• Deformable Convolutional Networks
• Uncertainty-aware Short-term Motion Prediction of Traffic Actors for\n Autonomous Driving

Cited by

• HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval
• Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection
• From Keypoints to Predictive Distributions: Post-Hoc Uncertainty for YOLO-Pose Models
• Learning to Detect Label Errors by Making Them: A Method for Segmentation and Object Detection Datasets
• URNet: Uncertainty-aware Refinement Network for Event-based Stereo Depth Estimation
• CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes
• Communication-Efficient Multi-Agent 3D Detection via Hybrid Collaboration

Related

• Acquisition of Localization Confidence for Accurate Object Detection
• Universal Bounding Box Regression and Its Applications
• Focal and Efficient IOU Loss for Accurate Bounding Box Regression
• InterpIoU: Rethinking Bounding Box Regression with Interpolation-Based IoU Optimization
• Localization Uncertainty-Based Attention for Object Detection