Filter by type:

In NeurIPS, 2020.

Preprint, a shorter version accepted in MICCAI, 2020.

In Neuroimage, 2020.

In ICCV, Oral (top ~4%), * equal contributions, 2019.

In ICML, Oral, 2019.

In CVPR, 2019.

In MICCAI, Spotlight (top ~5%), 2018.

In MICCAI, 2018.

In MICCAI, 2018.

In ICML, Long Oral, 2018.

In NeuroImage, 2017.

In MICCAI, Oral and Best Paper Award (< 1%), 2017.

We propose a Bayesian variant of random forests, which provides an estimate of uncertainty over prediction which can be used to assess its accuracy in the absence of ground truth. We have shown that the predictive uncertainly correlates well with the accuracy and can highlight abnormality not represented in the training data.
In MICCAI, 2016.