cs.CVNov 9, 2026

DUO: Dual Readouts of Diffusion Models for OOD Detection

Authors: Alireza Javid, Shirin Shoushtari, Nuria González Prelcic

Organizations: University of California, San Diego · Washington University in St. Louis

Abstract

Diffusion models are powerful generative methods for learning and sampling from complex data distributions. Safely deploying these models requires detecting inputs that fall outside their training distribution. Because diffusion models recover clean samples from noisy inputs, reconstruction error is often used for out-of-distribution (OOD) detection. This approach assumes that in-distribution (ID) inputs are reconstructed more accurately than OOD inputs. However, OOD inputs may be reconstructed equally well or even better, making this score unreliable. We therefore propose the leading sensitivity spectrum of intermediate denoising features as a complementary OOD signal and demonstrate that it remains informative when reconstruction error is misleading. We introduce DUal-readout of diffusion models for OOD detection (DUO), a fully unsupervised, training-free OOD detector that combines reconstruction error and feature sensitivity. DUO improves average AUROC by approximately 6% points over the strongest baselines while substantially reducing inference cost, and achieves SOTA on near-OOD and high-resolution benchmarks.

Figures & tables

Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Geometry over Density: Few-Shot Cross-Domain OOD Detection

    May 5, 2026Shawn Li, You Qin, Jiate Li +4Diffusion-Based OOD DetectionDistribution Shift Detection

  2. Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model

    Sep 16, 2024Kun Fang, Zuopeng Yang, Haibo Hu +3Diffusion-Based OOD DetectionOOD Detection