Instance-Level Post Hoc Uncertainty Quantification in Object Detection

2026-06-03 · Chongzhe Zhang, Zifan Zeng, Qunli Zhang, Feng Liu, Zheng Hu arxiv

Object detection is a safety-critical component of autonomous driving. It is essential to quantify the uncertainty in bounding-box predictions for safety assurance. Post hoc uncertainty quantification without retraining aligns with real-world deployment requirements; therefore, we employ the Laplace approximation. Because instance-level uncertainty is needed, linearized inference methods that require multiple backpropagations are not time-efficient, and sampling-based methods are not fully post hoc. We propose Monte-Carlo generalized linearized model (MC-GLM), which provides instance-level and approximately post hoc uncertainty quantification. The number of samples required in the Monte Carlo step is constant and independent of the number of output instances, so it can be parallelized. Experiments on the nuScenes dataset with the CenterPoint detector validate the effectiveness of our method, and the resulting uncertainties exhibit good quality.

📄 PDF Abstract BibTeX arXiv:2606.04656

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving Object Detection

SGPMIL: Sparse Gaussian Process Multiple Instance Learning

2025-07-11 · Andreas Lolos, Stergios Christodoulidis, Aris L. Moustakas, Jose Dolz 외 arxiv

Multiple Instance Learning (MIL) offers a natural solution for settings where only coarse, bag-level labels are available, without having access to instance-level annotations. This is usually the case in digital patholog…

Multiple Instance Learning Gaussian Processes

Uncertainty Quantification via Neural Posterior Principal Components

2023-09-27 · NeurIPS 2023 11

Uncertainty quantification is crucial for the deployment of image restoration models in safety-critical domains, like autonomous driving and biological imaging. To date, methods for uncertainty visualization have mainly …

Autonomous Driving Denoising Image Denoising Image Restoration+4

MORI-Seg: Learning Morphological Geometry for Instance Segmentation without Instance Annotations

2026-05-27 · Leiyue Zhao, Tianyu Shi, Daniel Reisenbuchler, Xinzi He 외 arxiv

Instance-level quantification of kidney functional units is essential for morphometric analysis, yet most publicly available pathology datasets provide only semantic segmentation annotations, where adjacent structures of…

Semantic Segmentation Instance Segmentation

Bayesian BiLO: Bilevel Local Operator Learning for Efficient Uncertainty Quantification of Bayesian PDE Inverse Problems with Low-Rank Adaptation

2025-07-22 · Ray Zirui Zhang, Christopher E. Miles, Xiaohui Xie, John S. Lowengrub arxiv

Uncertainty quantification in PDE inverse problems is essential in many applications. Scientific machine learning and AI enable data-driven learning of model components while preserving physical structure, and provide th…

Bayesian Inference

Efficient Data Association and Uncertainty Quantification for Multi-Object Tracking

2020-11-13 · David S. Hayden, Sue Zheng, John W. Fisher III

Robust data association is critical for analysis of long-term motion trajectories in complex scenes. In its absence, trajectory precision suffers due to periods of kinematic ambiguity degrading the quality of follow-on a…

Multi-Object Tracking Object Tracking Scheduling Uncertainty Quantification