Anomaly Detection for imbalanced datasets with Deep Generative Models

TL;DR

This paper explores using deep generative models like GANs and VAEs for anomaly detection in imbalanced datasets, particularly in medical imaging, highlighting both successes and current limitations.

Contribution

It evaluates the effectiveness of state-of-the-art generative models for anomaly detection in real-world imbalanced datasets, revealing challenges in complex data scenarios.

Findings

GANs and VAEs can distinguish anomalies in MNIST data.

Models struggle to capture complexity in NLST medical data.

Generative models face challenges in broad anomaly detection applications.

Abstract

Many important data analysis applications present with severely imbalanced datasets with respect to the target variable. A typical example is medical image analysis, where positive samples are scarce, while performance is commonly estimated against the correct detection of these positive examples. We approach this challenge by formulating the problem as anomaly detection with generative models. We train a generative model without supervision on the `negative' (common) datapoints and use this model to estimate the likelihood of unseen data. A successful model allows us to detect the `positive' case as low likelihood datapoints. In this position paper, we present the use of state-of-the-art deep generative models (GAN and VAE) for the estimation of a likelihood of the data. Our results show that on the one hand both GANs and VAEs are able to separate the `positive' and `negative' samples in the MNIST case. On the other hand, for the NLST case, neither GANs nor VAEs were able to capture the complexity of the data and discriminate anomalies at the level that this task requires. These results show that even though there are a number of successes presented in the literature for using generative models in similar applications, there remain further challenges for broad successful implementation.