ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detection

03/12/2020
by   Mohammadreza Salehi, et al.
18

Autoencoders (AE) have recently been widely employed to approach the novelty detection problem. Trained only on the normal data, the AE is expected to reconstruct the normal data effectively while fail to regenerate the anomalous data, which could be utilized for novelty detection. However, in this paper, it is demonstrated that this does not always hold. AE often generalizes so perfectly that it can also reconstruct the anomalous data well. To address this problem, we propose a novel AE that can learn more semantically meaningful features. Specifically, we exploit the fact that adversarial robustness promotes learning of meaningful features. Therefore, we force the AE to learn such features by penalizing networks with a bottleneck layer that is unstable against adversarial perturbations. We show that despite using a much simpler architecture in comparison to the prior methods, the proposed AE outperforms or is competitive to state-of-the-art on three benchmark datasets.

READ FULL TEXT

page 3

page 12

page 13

page 14

research
03/27/2021

OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection

Novelty detection is the task of recognizing samples that do not belong ...
research
05/28/2022

Fake It Till You Make It: Near-Distribution Novelty Detection by Score-Based Generative Models

We aim for image-based novelty detection. Despite considerable progress,...
research
03/19/2023

PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies

Due to the rarity of anomalous events, video anomaly detection is typica...
research
07/06/2018

Generative Probabilistic Novelty Detection with Adversarial Autoencoders

Novelty detection is the problem of identifying whether a new data point...
research
06/01/2020

Deep Context-Aware Novelty Detection

A common assumption of novelty detection is that the distribution of bot...
research
09/29/2019

Natural representation of composite data with replicated autoencoders

Generative processes in biology and other fields often produce data that...
research
06/09/2020

Novelty Detection via Robust Variational Autoencoding

We propose a new method for novelty detection that can tolerate nontrivi...

Please sign up or login with your details

Forgot password? Click here to reset