OEST: OUTLIER EXPOSURE BY SIMPLE TRANSFORMATIONS FOR OUT-OF-DISTRIBUTION DETECTION

Although the previous works for out-of-distribution(OOD) detection have achieved great improvements, they are still highly dependent on the specific selection of the outliers from external datasets or that transformed by certain data augmentations, and hence cannot be applied in a wide range of domains. However, the auxiliary impact of some simple transformations has been ignored. In this paper, we propose a simple, yet effective method called Exposing by Simple Transformations (EST), which aims at exposing the out- liers by the composition of several simple transformations of data augmentations via energy score. In addition, our training scheme can make full use of nearly all considered data augmentations in previous works, even though some of them are generally regarded as useless. And we also find that, for simple data augmentation, our training scheme is less time-consuming and better in performance than relative works. Furthermore, we prove that our method outperforms the state-of-the-art methods.