Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection

TL;DR

This paper explores the trade-off in VAE-based anomaly detection between reconstruction quality and detection performance, proposing methods like beta-scheduling and Sparse VAE to improve both.

Contribution

It identifies the reconstruction-detection trade-off in $eta$-VAEs and introduces two mitigation strategies, with Sparse VAE notably enhancing detection without sacrificing reconstruction.

Findings

Models with constrained latent space improve detection metrics.

Detection performance variability is linked to latent distribution distance.

Sparse VAE enhances detection while maintaining high reconstruction quality.

Abstract

Variational autoencoders are widely used for unsupervised anomaly detection. Model selection however remains an open-question: to remain fully unsupervised, hyperparameters are often chosen to minimize the reconstruction error on normal samples. In this paper, we reveal a trade-off between reconstruction quality and anomaly detection among $\beta$-VAE models. Models with constrained latent space reach higher detection metrics but lower reconstruction quality. We also assess the performance variability across random seeds and show it is linked to the distance between normal and abnormal latent distributions. From this analysis, we justify and investigate two methods to mitigate the reconstructiondetection tradeoff: beta-scheduling and the Sparse VAE. The latter especially shows an improvement in detection while maintaining high reconstruction quality.