Luca Ferragina

Enhancing anomaly detectors with LatentOut

2023 · Journal of Intelligent Information Systems

Abstract $${{\textbf{Latent}}\varvec{Out}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>Latent</mml:mi> <mml:mrow> <mml:mi>Out</mml:mi> </mml:mrow> </mml:mrow> </mml:math> is a recently introduced algorithm for unsupervised anomaly detection which enhances latent space-based neural methods, namely ( Variational ) Autoencoders , GANomaly and ANOGan …