Evaluating Unsupervised Methods for Out-of-Distribution Detection on Semantically Similar Image Data

Abstract: Out-of-distribution detection considers methods used to detect data that deviates from the underlying data distribution used to train some machine learning model. This is an important topic, as artificial neural networks have previously been shown to be capable of producing arbitrarily confident predictions, even for anomalous samples that deviate from the training distribution. Previous work has developed many reportedly effective methods for out-of-distribution detection, but these are often evaluated on data that is semantically different from the training data, and therefore does not necessarily reflect the true performance that these methods would show in more challenging conditions. In this work, six unsupervised out-of- distribution detection methods are evaluated and compared under more challenging conditions, in the context of classification of semantically similar image data using deep neural networks. It is found that the performance of all methods vary significantly across the tested datasets, and that no one method is consistently superior. Encouraging results are found for a method using ensembles of deep neural networks, but overall, the observed performance for all methods is considerably lower than in many related works, where easier tasks are used to evaluate the performance of these methods.