Normalizing Flows For Out of Distribution Detection via Latent Density Estimation

Evan Cook, Marc-Antoine Lavoie, Steven L. Waslander

Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)

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.

Keywords: Out-of-distribution detection, normalizing flow, image classification

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract:

Out-of-distribution (OOD) detection is a critical task for safe deployment of learning systems in the open world setting. In this work, we propose the use of latent density estimation via normalizing flows for the OOD task and present a fully unsupervised approach with no requirement for exposure to OOD data, avoiding researcher bias in OOD sample selection. This is a fully post-hoc method which can be applied to any pretrained model, and involves training a lightweight auxiliary normalizing flow model to perform the out-of-distribution detection via density thresholding. Experiments on OOD detection in image classification show strong results, including 98.2% AUROC for ImageNet-1k vs. Textures, which exceeds the state of the art by 8.4%. Further, we provide insights into training pitfalls that have plagued normalizing flows for use in 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.

Submission Number: 4578