We Know Where We Don't Know: 3D Bayesian CNNs for Credible Geometric Uncertainty

1 code implementation • 23 Oct 2019 • Tyler LaBonte, Carianne Martinez, Scott A. Roberts

The geometric uncertainty maps generated by our BCNN capture distributions of sigmoid values that are interpretable as confidence intervals, critical for applications that rely on deep learning for high-consequence decisions.

Bayesian Inference Computed Tomography (CT) +2