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.
@article{arxiv.1811.11210,
title = {Calibrating Uncertainties in Object Localization Task},
author = {Buu Phan and Rick Salay and Krzysztof Czarnecki and Vahdat Abdelzad and Taylor Denouden and Sachin Vernekar},
journal= {arXiv preprint arXiv:1811.11210},
year = {2018}
}