Deep Embedded Auto-encoder for End-to-End Unsupervised Image Anomaly Detection

Abstract Image anomaly detection plays a critical role in industrial quality control, medical diagnostics, and security surveillance, yet existing unsupervised methods often suffer from limited detection accuracy and poor adaptability. To overcome these limitations, we propose UAD-ADC, a novel frame...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuan Huang, Hailin Tang
Format: Article
Language:English
Published: Springer 2025-06-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Online Access:https://doi.org/10.1007/s44196-025-00860-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849726049496072192
author Xuan Huang
Hailin Tang
author_facet Xuan Huang
Hailin Tang
author_sort Xuan Huang
collection DOAJ
description Abstract Image anomaly detection plays a critical role in industrial quality control, medical diagnostics, and security surveillance, yet existing unsupervised methods often suffer from limited detection accuracy and poor adaptability. To overcome these limitations, we propose UAD-ADC, a novel framework that automatically identifies anomalies in images without requiring labeled training data. Our approach integrates deep representation learning with adaptive clustering to effectively separate normal patterns from anomalies by learning robust feature representations and dynamically refining decision boundaries. A key innovation is our intelligent sample selection mechanism, which enhances model stability by prioritizing high-confidence normal samples during training, along with an iterative optimization strategy that progressively improves anomaly discrimination. Extensive experiments on benchmark datasets demonstrate that UAD-ADC significantly outperforms state-of-the-art unsupervised methods, with particular effectiveness under varying anomaly ratios. These advancements pave the way for more reliable and scalable unsupervised anomaly detection in practical scenarios.
format Article
id doaj-art-a5bf907e160e4f4794371b3b03f4df5b
institution DOAJ
issn 1875-6883
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series International Journal of Computational Intelligence Systems
spelling doaj-art-a5bf907e160e4f4794371b3b03f4df5b2025-08-20T03:10:18ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832025-06-0118112210.1007/s44196-025-00860-1Deep Embedded Auto-encoder for End-to-End Unsupervised Image Anomaly DetectionXuan Huang0Hailin Tang1Chengdu College of University of Electronic Science and Technology of ChinaFaculty of Megadata and Computing, Guangdong Baiyun UniversityAbstract Image anomaly detection plays a critical role in industrial quality control, medical diagnostics, and security surveillance, yet existing unsupervised methods often suffer from limited detection accuracy and poor adaptability. To overcome these limitations, we propose UAD-ADC, a novel framework that automatically identifies anomalies in images without requiring labeled training data. Our approach integrates deep representation learning with adaptive clustering to effectively separate normal patterns from anomalies by learning robust feature representations and dynamically refining decision boundaries. A key innovation is our intelligent sample selection mechanism, which enhances model stability by prioritizing high-confidence normal samples during training, along with an iterative optimization strategy that progressively improves anomaly discrimination. Extensive experiments on benchmark datasets demonstrate that UAD-ADC significantly outperforms state-of-the-art unsupervised methods, with particular effectiveness under varying anomaly ratios. These advancements pave the way for more reliable and scalable unsupervised anomaly detection in practical scenarios.https://doi.org/10.1007/s44196-025-00860-1Anomaly detectionUnsupervised learningDeep clusteringAuto-encoderFeature representationEnd-to-end
spellingShingle Xuan Huang
Hailin Tang
Deep Embedded Auto-encoder for End-to-End Unsupervised Image Anomaly Detection
International Journal of Computational Intelligence Systems
Anomaly detection
Unsupervised learning
Deep clustering
Auto-encoder
Feature representation
End-to-end
title Deep Embedded Auto-encoder for End-to-End Unsupervised Image Anomaly Detection
title_full Deep Embedded Auto-encoder for End-to-End Unsupervised Image Anomaly Detection
title_fullStr Deep Embedded Auto-encoder for End-to-End Unsupervised Image Anomaly Detection
title_full_unstemmed Deep Embedded Auto-encoder for End-to-End Unsupervised Image Anomaly Detection
title_short Deep Embedded Auto-encoder for End-to-End Unsupervised Image Anomaly Detection
title_sort deep embedded auto encoder for end to end unsupervised image anomaly detection
topic Anomaly detection
Unsupervised learning
Deep clustering
Auto-encoder
Feature representation
End-to-end
url https://doi.org/10.1007/s44196-025-00860-1
work_keys_str_mv AT xuanhuang deepembeddedautoencoderforendtoendunsupervisedimageanomalydetection
AT hailintang deepembeddedautoencoderforendtoendunsupervisedimageanomalydetection