Generative Ensembles for Robust Anomaly Detection

by   Hyunsun Choi, et al.

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.


page 3

page 6


Are generative deep models for novelty detection truly better?

Many deep models have been recently proposed for anomaly detection. This...

Perfect density models cannot guarantee anomaly detection

Thanks to the tractability of their likelihood, some deep generative mod...

Anomaly Detection for imbalanced datasets with Deep Generative Models

Many important data analysis applications present with severely imbalanc...

Consistency-based anomaly detection with adaptive multiple-hypotheses predictions

In out-of-distribution classification tasks, only some classes - the nor...

Unsupervised Out-of-Distribution Detection with Batch Normalization

Likelihood from a generative model is a natural statistic for detecting ...

Anomaly Machine Component Detection by Deep Generative Model with Unregularized Score

One of the most common needs in manufacturing plants is rejecting produc...

Please sign up or login with your details

Forgot password? Click here to reset