Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models
This addresses reliability and safety issues in machine learning systems, particularly for image data, but is incremental as it builds on existing likelihood-based methods.
The paper tackles the problem of out-of-distribution detection in deep probabilistic generative models, which often assign high likelihoods to outliers, by proposing a new detection metric that avoids outlier exposure and achieves state-of-the-art performance on various models.
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.