Work

Adversarial autoencoders for novelty detection

Year: 2017

Type: report

Abstract: In this paper, we address the problem of novelty detection, 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.

Source: HAL

Authors: Leveau, Valentin, Joly, Alexis

Institution: Laboratoire d'Informatique, de Robotique et de Microélectronique de Montpellier

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2885367966

Cites:

Cited by: 15

Related to: 10