Adversarial autoencoders for novelty detection - Archive ouverte HAL Access content directly
Reports (Research Report) Year : 2017

Adversarial autoencoders for novelty detection

(1) , (1)
1
Valentin Leveau
  • Function : Author
  • PersonId : 961045
Alexis Joly

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.
Fichier principal
Vignette du fichier
valentin.pdf (3.41 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01636617 , version 1 (16-11-2017)

Identifiers

  • HAL Id : hal-01636617 , version 1

Cite

Valentin Leveau, Alexis Joly. Adversarial autoencoders for novelty detection. [Research Report] Inria - Sophia Antipolis. 2017. ⟨hal-01636617⟩
537 View
878 Download

Share

Gmail Facebook Twitter LinkedIn More