# Instance-Level Post Hoc Uncertainty Quantification in Object Detection

arXiv: https://arxiv.org/abs/2606.04656 · HTML: https://mlsanity.com/paper/2606.04656/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Optimizing Neural Networks with Kronecker-factored Approximate Curvature](https://mlsanity.com/paper/1503.05671/) (2015)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference](https://mlsanity.com/paper/1506.02158/) (2015)
- [Practical Deep Learning with Bayesian Principles](https://mlsanity.com/paper/1906.02506/) (2019)
- [Hyperparameter Ensembles for Robustness and Uncertainty Quantification](https://mlsanity.com/paper/2006.13570/) (2020)
- [Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis](https://mlsanity.com/paper/1806.03884/) (2018)
- [Evaluating Bayesian Deep Learning Methods for Semantic Segmentation](https://mlsanity.com/paper/1811.12709/) (2018)
- [Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors](https://mlsanity.com/paper/1603.04733/) (2016)
- [BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors](https://mlsanity.com/paper/1903.03838/) (2019)
- [Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors](https://mlsanity.com/paper/2101.05036/) (2021)
- [Estimating Model Uncertainty of Neural Networks in Sparse Information Form](https://mlsanity.com/paper/2006.11631/) (2020)
- [Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving](https://mlsanity.com/paper/1909.12358/) (2019)
- [Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction](https://mlsanity.com/paper/2403.07263/) (2024)
- [Monte Carlo DropBlock for Modelling Uncertainty in Object Detection](https://mlsanity.com/paper/2108.03614/) (2021)
- [Eigenvalue Corrected Noisy Natural Gradient](https://mlsanity.com/paper/1811.12565/) (2018)
- [Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction](https://mlsanity.com/paper/2210.07424/) (2022)

## Abstract (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.