Tag
This paper compares cross-validation ensembles to deep ensembles for uncertainty estimation in medical image segmentation. Deep ensembles outperform cross-validation ensembles in calibration and failure detection, while cross-validation ensembles better approximate inter-rater variability.
bde is a Python package that brings sampling-based Bayesian Deep Learning to practitioners via the MILE method, combining JAX's speed with scikit-learn's API for tabular supervised learning tasks.