Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models

TL;DR

This paper introduces a new OOD detection metric for deep probabilistic generative models that does not require outlier exposure, demonstrating robustness and state-of-the-art performance across various models.

Contribution

The paper proposes a likelihood ratio-based OOD detection method that operates without auxiliary outliers or additional training, improving robustness and efficiency.

Findings

Achieves state-of-the-art OOD detection performance

Robust to diverse image variations

Does not require auxiliary models or training

Abstract

Out-of-distribution (OOD) detection is an important task in machine learning systems for ensuring their reliability and safety. Deep probabilistic generative models facilitate OOD detection by estimating the likelihood of a data sample. However, such models frequently assign a suspiciously high likelihood to a specific outlier. Several recent works have addressed this issue by training a neural network with auxiliary outliers, which are generated by perturbing the input data. In this paper, we discover that these approaches fail for certain OOD datasets. Thus, we suggest a new detection metric that operates without outlier exposure. We observe that our metric is robust to diverse variations of an image compared to the previous outlier-exposing methods. Furthermore, our proposed score requires neither auxiliary models nor additional training. Instead, this paper utilizes the likelihood ratio statistic in a new perspective to extract genuine properties from the given single deep probabilistic generative model. We also apply a novel numerical approximation to enable fast implementation. Finally, we demonstrate comprehensive experiments on various probabilistic generative models and show that our method achieves state-of-the-art performance.