|Title||Calibrating Uncertainties in Object Localization Task|
|Publication Type||Conference Paper|
|Year of Publication||2018|
|Authors||Phan, B. Truong, R. Salay, K. Czarnecki, V. Abdelzad, T. Denouden, and S. Vernekar|
|Conference Name||Third workshop on Bayesian Deep Learning (NeurIPS 2018), Montréal, Canada.|
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.