Post-hoc Uncertainty Calibration for Domain Drift Scenarios [article]

Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem, Daniel Cremers, Florian Buettner
2021 arXiv   pre-print
We address the problem of uncertainty calibration. While standard deep neural networks typically yield uncalibrated predictions, calibrated confidence scores that are representative of the true likelihood of a prediction can be achieved using post-hoc calibration methods. However, to date the focus of these approaches has been on in-domain calibration. Our contribution is two-fold. First, we show that existing post-hoc calibration methods yield highly over-confident predictions under domain
more » ... t. Second, we introduce a simple strategy where perturbations are applied to samples in the validation set before performing the post-hoc calibration step. In extensive experiments, we demonstrate that this perturbation step results in substantially better calibration under domain shift on a wide range of architectures and modelling tasks.
arXiv:2012.10988v2 fatcat:ngm2tccxqna33g4acyedur6d54