DeepAI AI Chat
Log In Sign Up

Are Bayesian neural networks intrinsically good at out-of-distribution detection?

by   Christian Henning, et al.

The need to avoid confident predictions on unfamiliar data has sparked interest in out-of-distribution (OOD) detection. It is widely assumed that Bayesian neural networks (BNN) are well suited for this task, as the endowed epistemic uncertainty should lead to disagreement in predictions on outliers. In this paper, we question this assumption and provide empirical evidence that proper Bayesian inference with common neural network architectures does not necessarily lead to good OOD detection. To circumvent the use of approximate inference, we start by studying the infinite-width case, where Bayesian inference can be exact considering the corresponding Gaussian process. Strikingly, the kernels induced under common architectural choices lead to uncertainties that do not reflect the underlying data generating process and are therefore unsuited for OOD detection. Finally, we study finite-width networks using HMC, and observe OOD behavior that is consistent with the infinite-width case. Overall, our study discloses fundamental problems when naively using BNNs for OOD detection and opens interesting avenues for future research.


page 4

page 7

page 8

page 9

page 11


Uncertainty-based out-of-distribution detection requires suitable function space priors

The need to avoid confident predictions on unfamiliar data has sparked i...

Deep Maxout Network Gaussian Process

Study of neural networks with infinite width is important for better und...

An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks

Comparing Bayesian neural networks (BNNs) with different widths is chall...

An Overview of Uncertainty Quantification Methods for Infinite Neural Networks

To better understand the theoretical behavior of large neural networks, ...

Bayesian neural network unit priors and generalized Weibull-tail property

The connection between Bayesian neural networks and Gaussian processes g...

Why bigger is not always better: on finite and infinite neural networks

Recent work has shown that the outputs of convolutional neural networks ...