Abstract: One critical challenge in deploying machine learning models in real-life applications is out-of-distribution (OOD) detection. Given a predictive model which is accurate on in distribution (ID) data, an OOD detection system can further equip the model with the option to defer prediction when the input is novel and the model has low confidence. Notably, there has been some recent interest in utilizing gradient information in pretrained models for OOD detection. While these methods are competitive, we argue that previous works conflate their performance with the necessity of gradients. In this work, we provide an in-depth analysis of gradient-based methods and elucidate the key components that warrant their OOD detection performance. We further demonstrate that a general, non-gradient-based family of OOD detection methods are just as competitive, casting doubt on the usefulness of gradients for OOD detection
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: Deep Learning and representational learning