Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification
Matias Valdenegro-Toro
In 4th Bayesian Deep Learning Workshop - NeurIPS 2019 Workshop, 13.12.-13.12.2019, Vancouver, BC, Keine, Dec/2019.

Zusammenfassung (Abstract) :

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.

Links:

https://arxiv.org/abs/1910.08168


© DFKI GmbH
zuletzt geändert am 27.02.2023
nach oben