Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification
This provides a faster uncertainty estimation method for robust robotics applications, but it is incremental as it builds on Deep Ensembles with a trade-off in accuracy.
The paper tackles the computational expense of Deep Ensembles for uncertainty estimation in image classification by proposing deep sub-ensembles, which ensemble only layers near the output, achieving speedups of 1.5-2.5x on CIFAR10 and up to 5-15x on SVHN with small increases in error and negative log-likelihood.
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, and not the whole model. With ResNet-20 on the CIFAR10 dataset, we obtain 1.5-2.5 speedup over a Deep Ensemble, with a small increase in error and NLL, and similarly up to 5-15 speedup with a VGG-like network on the SVHN dataset. Our results show that this idea enables a trade-off between error and uncertainty quality versus computational performance.