Generative Ensembles for Robust Anomaly DetectionDownload PDF

27 Sept 2018 (modified: 22 Oct 2023)ICLR 2019 Conference Blind SubmissionReaders: Everyone
Abstract: Deep generative models are capable of learning probability distributions over large, high-dimensional datasets such as images, video and natural language. Generative models trained on samples from p(x) ought to assign low likelihoods to out-of-distribution (OoD) samples from q(x), making them suitable for anomaly detection applications. We show that in practice, likelihood models are themselves susceptible to OoD errors, and even assign large likelihoods to images from other natural datasets. To mitigate these issues, we propose Generative Ensembles, a model-independent technique for OoD detection that combines density-based anomaly detection with uncertainty estimation. Our method outperforms ODIN and VIB baselines on image datasets, and achieves comparable performance to a classification model on the Kaggle Credit Fraud dataset.
Keywords: Anomaly Detection, Uncertainty, Out-of-Distribution, Generative Models
TL;DR: We use generative models to perform out-of-distribution detection, and improve their robustness with uncertainty estimation.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 3 code implementations](https://www.catalyzex.com/paper/arxiv:1810.01392/code)
12 Replies

Loading