Out-of-distribution detection using normalizing flows on the data manifold

TL;DR

This paper introduces a novel out-of-distribution detection method using normalizing flows on data manifolds, which improves detection accuracy by estimating density on low-dimensional manifolds and combining it with data complexity measures.

Contribution

The authors propose a new approach that estimates likelihood on data manifolds and combines it with data complexity, enhancing out-of-distribution detection without model modifications.

Findings

Improved out-of-distribution detection performance with manifold-based density estimation.

Combining manifold likelihood with data complexity enhances detection accuracy.

Method does not require model structure changes or auxiliary OOD data during training.

Abstract

Using the intuition that out-of-distribution data have lower likelihoods, a common approach for out-of-distribution detection involves estimating the underlying data distribution. Normalizing flows are likelihood-based generative models providing a tractable density estimation via dimension-preserving invertible transformations. Conventional normalizing flows are prone to fail in out-of-distribution detection, because of the well-known curse of dimensionality problem of the likelihood-based models. To solve the problem of likelihood-based models, some works try to modify likelihood for example by incorporating a data complexity measure. We observed that these modifications are still insufficient. According to the manifold hypothesis, real-world data often lie on a low-dimensional manifold. Therefore, we proceed by estimating the density on a low-dimensional manifold and calculating a distance from the manifold as a measure for out-of-distribution detection. We propose a powerful criterion that combines this measure with the modified likelihood measure based on data complexity. Extensive experimental results show that incorporating manifold learning while accounting for the estimation of data complexity improves the out-of-distribution detection ability of normalizing flows. This improvement is achieved without modifying the model structure or using auxiliary out-of-distribution data during training.