# Calibrating Uncertainties in Object Localization Task

arXiv: https://arxiv.org/abs/1811.11210 · HTML: https://mlsanity.com/paper/1811.11210/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2018.

## Built on by (most cited first, 9 of 9)

- [Uncertainty for Identifying Open-Set Errors in Visual Object Detection](https://mlsanity.com/paper/2104.01328/) (2021)
- [BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks](https://mlsanity.com/paper/2207.06873/) (2022)
- [Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction](https://mlsanity.com/paper/2403.07263/) (2024)
- [Recalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imaging](https://mlsanity.com/paper/2104.12376/) (2021)
- [Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibration](https://mlsanity.com/paper/2306.08981/) (2023)
- [Likelihood Annealing: Fast Calibrated Uncertainty for Regression](https://mlsanity.com/paper/2302.11012/) (2023)
- [Towards Reliable Uncertainty Quantification via Deep Ensembles in Multi-output Regression Task](https://mlsanity.com/paper/2303.16210/) (2023)
- [TransMorph: Transformer for unsupervised medical image registration](https://mlsanity.com/paper/2111.10480/) (2021)
- [Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence](https://mlsanity.com/paper/2507.20272/) (2025)

## Abstract (arXiv)

In many safety-critical applications such as autonomous driving and surgical robots, it is desirable to obtain prediction uncertainties from object detection modules to help support safe decision-making. Specifically, such modules need to estimate the probability of each predicted object in a given region and the confidence interval for its bounding box. While recent Bayesian deep learning methods provide a principled way to estimate this uncertainty, the estimates for the bounding boxes obtained using these methods are uncalibrated. In this paper, we address this problem for the single-object localization task by adapting an existing technique for calibrating regression models. We show, experimentally, that the resulting calibrated model obtains more reliable uncertainty estimates.