On out-of-distribution detection with Bayesian neural networks

TL;DR

This paper critically examines the effectiveness of Bayesian neural networks for out-of-distribution detection, revealing fundamental limitations in their predictive uncertainties and suggesting that naive use may be ineffective.

Contribution

The paper demonstrates that common Bayesian neural network priors do not reliably reflect data distribution for OOD detection and highlights the need for more suitable prior design or alternative approaches.

Findings

Bayesian neural networks often produce unreliable OOD uncertainties.

Infinite-width BNNs with standard kernels do not improve OOD detection.

Trade-offs exist between generalization and OOD detection in BNNs.

Abstract

The question whether inputs are valid for the problem a neural network is trying to solve has sparked interest in out-of-distribution (OOD) detection. It is widely assumed that Bayesian neural networks (BNNs) 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 show that proper Bayesian inference with function space priors induced by neural networks 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 due to the correspondence with Gaussian processes. Strikingly, the kernels derived from common architectural choices lead to function space priors which induce predictive uncertainties that do not reflect the underlying input data distribution and are therefore unsuited for OOD detection. Importantly, we find the OOD behavior in this limiting case to be consistent with the corresponding finite-width case. To overcome this limitation, useful function space properties can also be encoded in the prior in weight space, however, this can currently only be applied to a specified subset of the domain and thus does not inherently extend to OOD data. Finally, we argue that a trade-off between generalization and OOD capabilities might render the application of BNNs for OOD detection undesirable in practice. Overall, our study discloses fundamental problems when naively using BNNs for OOD detection and opens interesting avenues for future research.