Adversarial Autoencoders for Novelty Detection

Valentin Leveau, Alexis Joly

Abstract: In this paper, we address the problem of novelty detection, \textit{i.e} recognizing at test time if a data item comes from the training data distribution or not. We focus on Adversarial autoencoders (AAE) that have the advantage to explicitly control the distribution of the known data in the feature space. We show that when they are trained in a (semi-)supervised way, they provide consistent novelty detection improvements compared to a classical autoencoder. We further improve their performance by introducing an explicit rejection class in the prior distribution coupled with random input images to the autoencoder.

Conflicts: inria.fr

Keywords: Deep learning, Unsupervised Learning, Semi-Supervised Learning