# Post-hoc Uncertainty Calibration for Domain Drift Scenarios Source: [Post-hoc Uncertainty Calibration for Domain Drift Scenarios]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:18:37.363Z Authors: Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem, Daniel Cremers, Florian Buettner Published: 2020-12-20T18:21:13.000Z ## Abstract 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 shift. 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. ## 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. - [Class-Incremental Learning on TinyImageNet (test)](): Class-incremental learning; TinyImageNet (test); Accuracy: 31.48. - [Class-Incremental Learning on CIFAR-100 (test) with Accuracy and Calibration Metrics](): Class-incremental learning; CIFAR-100 (test); Accuracy: 56.25. ## Original sources and implementation [Original paper]() [PDF]()