Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification

Matias Valdenegro-Toro

In: 4th Bayesian Deep Learning Workshop - NeurIPS 2019 Workshop. Workshop on Bayesian Deep Learning, located at NeurIPS2019, December 13, Vancouver, BC, Canada, Keine, 12/2019.


Fast estimates of model uncertainty are required for many robust robotics applications. Deep Ensembles provides state of the art uncertainty without requiring Bayesian methods, but still it is computationally expensive. In this paper we propose deep sub-ensembles, an approximation to deep ensembles where the core idea is to ensemble only the layers close to the output. Our results show that this idea enables a trade-off between error and uncertainty quality versus computational performance.

Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence