Timezone: »

 
Decomposing Representations for Deterministic Uncertainty Estimation
Haiwen Huang · Joost van Amersfoort · Yarin Gal

@
in Bayesian Deep Learning »
Event URL: https://openreview.net/forum?id=NUgEE4S_8gJ »

Uncertainty estimation is a key component in any deployed machine learning system. One way to evaluate uncertainty estimation is using “out-of-distribution” (OoD) detection, that is, distinguishing between the training data distribution and an unseen different data distribution using uncertainty. In this work, we show that current feature density based uncertainty estimators cannot perform well consistently across different OoD detection settings. To solve this, we propose to decompose the learned representations and integrate the uncertainties estimated on them separately. Through experiments, we demonstrate that we can greatly improve the performance and the interpretability of the uncertainty estimation.

Author Information

Haiwen Huang (University of Oxford)
Joost van Amersfoort (University of Oxford)
Yarin Gal (University of Oxford)

More from the Same Authors