no code implementations • 16 Nov 2021 • Adaku Uchendu, Daniel Campoy, Christopher Menart, Alexandra Hildenbrandt
Bayesian Neural Networks (BNNs), unlike Traditional Neural Networks (TNNs) are robust and adept at handling adversarial attacks by incorporating randomness.
no code implementations • 23 Jan 2018 • James W. Davis, Christopher Menart, Muhammad Akbar, Roman Ilin
Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses.