Abstract
Despite their successes, deep neural networks still make unreliable
predictions when faced with test data drawn from a distribution different to
that of the training data, constituting a major problem for AI safety. While
this motivated a recent surge in interest in developing methods to detect such
out-of-distribution (OoD) inputs, a robust solution is still lacking. We
propose a new probabilistic, unsupervised approach to this problem based on a
Bayesian variational autoencoder model, which estimates a full posterior
distribution over the decoder parameters using stochastic gradient Markov chain
Monte Carlo, instead of fitting a point estimate. We describe how
information-theoretic measures based on this posterior can then be used to
detect OoD data both in input space as well as in the model's latent space. The
effectiveness of our approach is empirically demonstrated.
Users
Please
log in to take part in the discussion (add own reviews or comments).