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.
Related papers
Ranked by semantic similarity β how closely each paper's abstract matches this one (100% = near-identical topic).