# Calibrating Uncertainties in Object Localization Task

Source: [Calibrating Uncertainties in Object Localization Task](<https://www.sota2.com/research/paper/68fa651e1e209131cea087d6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:37.466Z

Authors: Buu Phan, Rick Salay, Krzysztof Czarnecki, Vahdat Abdelzad, Taylor Denouden, Sachin Vernekar

Published: 2018-11-27T19:27:29.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1811.11210>)

[PDF](<https://arxiv.org/pdf/1811.11210.pdf>)
