Improved Predictive Uncertainty using Corruption-based Calibration.
Year: 2021
Type: preprint
Abstract: We propose a simple post hoc calibration method to estimate the confidence/uncertainty that a model prediction is correct on data with covariate shift, as represented by the large-scale corrupted data benchmark [Ovadia et al, 2019]. We achieve this by synthesizing surrogate calibration sets by corrupting the calibration set with varying intensities of a known corruption. Our method demonstrates significant improvements on the benchmark on a wide range of covariate shifts.
Source: arXiv (Cornell University)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3172765007