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...
Saved in:
| Main Authors: | , |
|---|---|
| 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 |