On out-of-distribution detection with Bayesian neural networks
This study reveals fundamental limitations in using BNNs for OOD detection, which is crucial for safety-critical applications like autonomous systems, but it is incremental as it builds on existing assumptions and methods.
The paper tackles the problem of out-of-distribution (OOD) detection using Bayesian neural networks (BNNs), showing that proper Bayesian inference with common neural network priors does not necessarily lead to good OOD detection, as predictive uncertainties may not reflect the input data distribution, and suggests a trade-off between generalization and OOD capabilities might make BNNs undesirable for this task.
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.