Re-Benchmarking Out-of-Distribution Detection in Deep Neural Networks

Jinling Gao, Haoyue Bai, Lin Zhu, Nanyang Ye

Abstract: Out-of-distribution (OOD) detection is a key challenge for making machine learning models robust in the real world, where we want models to be aware of uncertainty outside their training data distribution. Despite the rapid development of existing OOD detection algorithms, their experimental settings are usually inconsistent, e.g., datasets, evaluation metrics, model selection, implementation choices. In this paper, we aim to understand OOD detection fundamentally and provide a comprehensive benchmarking of the current state of the art OOD detection methods in a consistent and realistic evaluation setting. This benchmarking contains a serious of datasets split, model selection criteria and OOD detection algorithms. This experimental framework can be easily extended to new algorithms, datasets, and model selection criteria. We conduct extensive experiments on this benchmark and find that the threshold of OOD detection algorithms are not consistent over different datasets and model selection criteria.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)