The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces

2026-05-21

AI Summary

Deep generative models often fail in out-of-distribution (OOD) detection due to unreliable likelihood estimates. This work proposes SITN, a method that leverages the diffeomorphic nature and mass-conservation property of continuous normalizing flows to perform an unsupervised goodness-of-fit test on individual samples within a factorized latent space. Requiring no OOD data and incurring low computational overhead, SITN rigorously controls the false positive rate and effectively mitigates the complexity bias inherent in conventional likelihood-based approaches. Empirical evaluations demonstrate that SITN achieves superior OOD detection performance on both standard benchmarks and synthetically perturbed datasets, significantly avoiding likelihood misinterpretation while enabling precise false positive control.

Abstract

Deep generative models offer a natural foundation for out-of-distribution (OOD) detection, yet prior work has shown that their assigned likelihoods are notoriously unreliable indicators for in- vs out-of-distribution data. In this paper, we address this problem by leveraging the diffeomorphic and mass-preserving properties of continuous normalising flows. Our analysis shows that OOD samples are mapped to noise samples that are highly atypical under the noise prior in ways not captured by the likelihood. Based on this observation, we propose a new method -- Signal in the Noise (SITN) -- for OOD detection on the single-sample level. SITN requires no access to OOD data, incurs minimal computational overhead, and provides strict control of false positive rates. Comprehensive evaluations through standard benchmarks and synthetic perturbations highlight the method's effectiveness and the absence of the complexity bias inherent to likelihood-based methods.

Problem

• out-of-distribution detection
• deep generative models
• likelihood reliability
• OOD detection
• anomaly detection

Innovation

• out-of-distribution detection
• normalising flows
• goodness-of-fit testing
• latent space
• likelihood-free OOD