# Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibration

arXiv: https://arxiv.org/abs/2306.08981 · HTML: https://mlsanity.com/paper/2306.08981/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 15 Jun 2023.

## Builds on (most cited first, 22 of 22)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Accurate Uncertainties for Deep Learning Using Calibrated Regression](https://mlsanity.com/paper/1807.00263/) (2018)
- [Bounding Box Regression with Uncertainty for Accurate Object Detection](https://mlsanity.com/paper/1809.08545/) (2018)
- [A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving](https://mlsanity.com/paper/2011.10671/) (2020)
- [TensorFlow Distributions](https://mlsanity.com/paper/1711.10604/) (2017)
- [Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving](https://mlsanity.com/paper/1904.04620/) (2019)
- [Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection](https://mlsanity.com/paper/1804.05132/) (2018)
- [BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors](https://mlsanity.com/paper/1903.03838/) (2019)
- [Uncertainty Estimation in One-Stage Object Detection](https://mlsanity.com/paper/1905.10296/) (2019)
- [Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference](https://mlsanity.com/paper/1909.13550/) (2019)
- [Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving](https://mlsanity.com/paper/1909.12358/) (2019)
- [Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection](https://mlsanity.com/paper/1809.05590/) (2018)
- [Recalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imaging](https://mlsanity.com/paper/2104.12376/) (2021)
- [Variational Inference based on Robust Divergences](https://mlsanity.com/paper/1710.06595/) (2017)
- [Calibrating Uncertainties in Object Localization Task](https://mlsanity.com/paper/1811.11210/) (2018)

## Built on by (most cited first, 5 of 5)

- [Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection](https://mlsanity.com/paper/2404.17427/) (2024)
- [Streamlining the Development of Active Learning Methods in Real-World Object Detection](https://mlsanity.com/paper/2508.19906/) (2025)
- [Prediction Accuracy & Reliability: Classification and Object Localization under Distribution Shift](https://mlsanity.com/paper/2409.03543/) (2024)
- [Probabilistic Object Detection with Conformal Prediction](https://mlsanity.com/paper/2605.07549/) (2026)
- [From Model Uncertainty to Human Attention: Localization-Aware Visual Cues for Scalable Annotation Review](https://mlsanity.com/paper/2605.12303/) (2026)

## Abstract (arXiv)

Robustly and accurately localizing objects in real-world environments can be challenging due to noisy data, hardware limitations, and the inherent randomness of physical systems. To account for these factors, existing works estimate the aleatoric uncertainty of object detectors by modeling their localization output as a Gaussian distribution N(μ,,σ2),, and training with loss attenuation. We identify three aspects that are unaddressed in the state of the art, but warrant further exploration: (1) the efficient and mathematically sound propagation of N(μ,,σ2), through non-linear post-processing, (2) the calibration of the predicted uncertainty, and (3) its interpretation. We overcome these limitations by: (1) implementing loss attenuation in EfficientDet, and proposing two deterministic methods for the exact and fast propagation of the output distribution, (2) demonstrating on the KITTI and BDD100K datasets that the predicted uncertainty is miscalibrated, and adapting two calibration methods to the localization task, and (3) investigating the correlation between aleatoric uncertainty and task-relevant error sources. Our contributions are: (1) up to five times faster propagation while increasing localization performance by up to 1%, (2) up to fifteen times smaller expected calibration error, and (3) the predicted uncertainty is found to correlate with occlusion, object distance, detection accuracy, and image quality.