On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection

07/15/2022
by   Guoxuan Xia, et al.
0

The ability to detect Out-of-Distribution (OOD) data is important in safety-critical applications of deep learning. The aim is to separate In-Distribution (ID) data drawn from the training distribution from OOD data using a measure of uncertainty extracted from a deep neural network. Deep Ensembles are a well-established method of improving the quality of uncertainty estimates produced by deep neural networks, and have been shown to have superior OOD detection performance compared to single models. An existing intuition in the literature is that the diversity of Deep Ensemble predictions indicates distributional shift, and so measures of diversity such as Mutual Information (MI) should be used for OOD detection. We show experimentally that this intuition is not valid on ImageNet-scale OOD detection – using MI leads to 30-40 We suggest an alternative explanation for Deep Ensembles' better OOD detection performance – OOD detection is binary classification and we are ensembling diverse classifiers. As such we show that practically, even better OOD detection performance can be achieved for Deep Ensembles by averaging task-specific detection scores such as Energy over the ensemble.

READ FULL TEXT
research
06/15/2020

Neural Ensemble Search for Performant and Calibrated Predictions

Ensembles of neural networks achieve superior performance compared to st...
research
02/14/2022

Deep Ensembles Work, But Are They Necessary?

Ensembling neural networks is an effective way to increase accuracy, and...
research
06/18/2019

Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles

The inaccuracy of neural network models on inputs that do not stem from ...
research
01/14/2021

DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation

Deep ensembles perform better than a single network thanks to the divers...
research
10/19/2022

Distribution Shift Detection for Deep Neural Networks

To deploy and operate deep neural models in production, the quality of t...
research
03/22/2018

Understanding Measures of Uncertainty for Adversarial Example Detection

Measuring uncertainty is a promising technique for detecting adversarial...
research
09/04/2023

Uncertainty in AI: Evaluating Deep Neural Networks on Out-of-Distribution Images

As AI models are increasingly deployed in critical applications, ensurin...

Please sign up or login with your details

Forgot password? Click here to reset