DualAD: Dual adversarial network for image anomaly detection⋆

Abstract Anomaly Detection, also known as outlier detection, is critical in domains such as network security, intrusion detection, and fraud detection. One popular approach to anomaly detection is using autoencoders, which are trained to reconstruct input by minimising reconstruction error with the...

Full description

Saved in:
Bibliographic Details
Main Authors: Yonghao Wan, Aimin Feng
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Computer Vision
Subjects:
Online Access:https://doi.org/10.1049/cvi2.12297
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850102629900746752
author Yonghao Wan
Aimin Feng
author_facet Yonghao Wan
Aimin Feng
author_sort Yonghao Wan
collection DOAJ
description Abstract Anomaly Detection, also known as outlier detection, is critical in domains such as network security, intrusion detection, and fraud detection. One popular approach to anomaly detection is using autoencoders, which are trained to reconstruct input by minimising reconstruction error with the neural network. However, these methods usually suffer from the trade‐off between normal reconstruction fidelity and abnormal reconstruction distinguishability, which damages the performance. The authors find that the above trade‐off can be better mitigated by imposing constraints on the latent space of images. To this end, the authors propose a new Dual Adversarial Network (DualAD) that consists of a Feature Constraint (FC) module and a reconstruction module. The method incorporates the FC module during the reconstruction training process to impose constraints on the latent space of images, thereby yielding feature representations more conducive to anomaly detection. Additionally, the authors employ dual adversarial learning to model the distribution of normal data. On the one hand, adversarial learning was implemented during the reconstruction process to obtain higher‐quality reconstruction samples, thereby preventing the effects of blurred image reconstructions on model performance. On the other hand, the authors utilise adversarial training of the FC module and the reconstruction module to achieve superior feature representation, making anomalies more distinguishable at the feature level. During the inference phase, the authors perform anomaly detection simultaneously in the pixel and latent spaces to identify abnormal patterns more comprehensively. Experiments on three data sets CIFAR10, MNIST, and FashionMNIST demonstrate the validity of the authors’ work. Results show that constraints on the latent space and adversarial learning can improve detection performance.
format Article
id doaj-art-e1f89c9c9f884afb91311d910460feb0
institution DOAJ
issn 1751-9632
1751-9640
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Computer Vision
spelling doaj-art-e1f89c9c9f884afb91311d910460feb02025-08-20T02:39:43ZengWileyIET Computer Vision1751-96321751-96402024-12-011881138114810.1049/cvi2.12297DualAD: Dual adversarial network for image anomaly detection⋆Yonghao Wan0Aimin Feng1Nanjing University of Aeronautics and Astronautics Nanjing ChinaNanjing University of Aeronautics and Astronautics Nanjing ChinaAbstract Anomaly Detection, also known as outlier detection, is critical in domains such as network security, intrusion detection, and fraud detection. One popular approach to anomaly detection is using autoencoders, which are trained to reconstruct input by minimising reconstruction error with the neural network. However, these methods usually suffer from the trade‐off between normal reconstruction fidelity and abnormal reconstruction distinguishability, which damages the performance. The authors find that the above trade‐off can be better mitigated by imposing constraints on the latent space of images. To this end, the authors propose a new Dual Adversarial Network (DualAD) that consists of a Feature Constraint (FC) module and a reconstruction module. The method incorporates the FC module during the reconstruction training process to impose constraints on the latent space of images, thereby yielding feature representations more conducive to anomaly detection. Additionally, the authors employ dual adversarial learning to model the distribution of normal data. On the one hand, adversarial learning was implemented during the reconstruction process to obtain higher‐quality reconstruction samples, thereby preventing the effects of blurred image reconstructions on model performance. On the other hand, the authors utilise adversarial training of the FC module and the reconstruction module to achieve superior feature representation, making anomalies more distinguishable at the feature level. During the inference phase, the authors perform anomaly detection simultaneously in the pixel and latent spaces to identify abnormal patterns more comprehensively. Experiments on three data sets CIFAR10, MNIST, and FashionMNIST demonstrate the validity of the authors’ work. Results show that constraints on the latent space and adversarial learning can improve detection performance.https://doi.org/10.1049/cvi2.12297computer visionfeature extractionimage recognitionimage reconstructionvision defects
spellingShingle Yonghao Wan
Aimin Feng
DualAD: Dual adversarial network for image anomaly detection⋆
IET Computer Vision
computer vision
feature extraction
image recognition
image reconstruction
vision defects
title DualAD: Dual adversarial network for image anomaly detection⋆
title_full DualAD: Dual adversarial network for image anomaly detection⋆
title_fullStr DualAD: Dual adversarial network for image anomaly detection⋆
title_full_unstemmed DualAD: Dual adversarial network for image anomaly detection⋆
title_short DualAD: Dual adversarial network for image anomaly detection⋆
title_sort dualad dual adversarial network for image anomaly detection⋆
topic computer vision
feature extraction
image recognition
image reconstruction
vision defects
url https://doi.org/10.1049/cvi2.12297
work_keys_str_mv AT yonghaowan dualaddualadversarialnetworkforimageanomalydetection
AT aiminfeng dualaddualadversarialnetworkforimageanomalydetection