Out-of-Distribution Detection with a Single Unconditional Diffusion Model

Alvin Heng, Alexandre H. Thiery, Harold Soh

Abstract

Out-of-distribution (OOD) detection is a critical task in machine learning that seeks to identify abnormal samples. Traditionally, unsupervised methods utilize a deep generative model for OOD detection. However, such approaches necessitate a different model when evaluating abnormality against a new distribution. With the emergence of foundational generative models, this paper explores whether a single generalist model can also perform OOD detection across diverse tasks. To that end, we introduce our method, Diffusion Paths, (DiffPath) in this work. DiffPath proposes to utilize a single diffusion model originally trained to perform unconditional generation for OOD detection. Specifically, we introduce a novel technique of measuring the rate-of-change and curvature of the diffusion paths connecting samples to the standard normal. Extensive experiments show that with a single model, DiffPath outperforms prior work on a variety of OOD tasks involving different distributions.
BibTeX
@inproceedings{heng2024out,
  author = {Alvin Heng and Alexandre H. Thiery and Harold Soh},
  title = {{Out-of-Distribution Detection with a Single Unconditional Diffusion Model}},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2024},
  url = {https://openreview.net/forum?id=tTnFH7D1h4},
}
Figure