Out of Distribution Data Detection Using Dropout Bayesian Neural Networks

02/18/2022
by   Andre T. Nguyen, et al.
0

We explore the utility of information contained within a dropout based Bayesian neural network (BNN) for the task of detecting out of distribution (OOD) data. We first show how previous attempts to leverage the randomized embeddings induced by the intermediate layers of a dropout BNN can fail due to the distance metric used. We introduce an alternative approach to measuring embedding uncertainty, justify its use theoretically, and demonstrate how incorporating embedding uncertainty improves OOD data identification across three tasks: image classification, language classification, and malware detection.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset