We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a network's classification calibration as well as its ability to detect out-of-distribution data. Without explicitly being designed to do so, VIB gives two natural metrics for handling and quantifying uncertainty.
@article{arxiv.1807.00906,
title = {Uncertainty in the Variational Information Bottleneck},
author = {Alexander A. Alemi and Ian Fischer and Joshua V. Dillon},
journal= {arXiv preprint arXiv:1807.00906},
year = {2018}
}
Comments
10 pages, 7 figures. Accepted to UAI 2018 - Uncertainty in Deep Learning Workshop