Out of Distribution Data Detection Using Dropout Bayesian Neural Networks
This work addresses the challenge of reliable out-of-distribution detection for machine learning systems, offering an incremental improvement over prior methods.
The paper tackled the problem of detecting out-of-distribution data by improving the use of dropout Bayesian neural networks, showing that incorporating embedding uncertainty enhances identification across image classification, language classification, and malware detection tasks.
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.