.png){kind=icon}
返回
Distributed Anomaly Detection With Attention-Guided Diffusion Models and Client-Side Defect Generation
.png){kind=icon}
PRE
AI
DOI：10.1109/JSYST.2025.3619401.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Modern industrial systems are increasingly defined by geographically distributed production lines, stringent privacy constraints, particularly to protect intellectual property and manufacturing process details, and heterogeneous data pipelines. In such environments, centralized anomaly detection (AD) is often impractical due to data governance restrictions and limited computational resources at local sites. To address these challenges, we propose a modular and lightweight AD framework based on diffusion models, named D-ADDA (distributed anomaly detection based on data augmentation), designed for distributed deployment. Unlike many state-of-the-art methods that depend on large pretrained models or external datasets, our approach is trained entirely on defective data locally available, enhancing privacy and domain specificity. A novel data augmentation module generates diverse defective samples through a multistage pipeline, which are used to train an attention-based diffusion model for defect synthesis. This architecture supports dislocated components across multiple clients, enabling training and inference in resource-constrained or privacy-sensitive settings. Experimental results on the MVTec AD dataset confirm the effectiveness of our approach, achieving an average classification accuracy of 60.46% across 14 categories, outperforming state-of-the-art approaches, with competitive localization performance.
Keyword:
Attention mechanism
data augmentation
defect synthesis
diffusion process
distributed anomaly detection (AD)
期刊
I
IF:
4.4
论文数:
131
被引数:
0
机构
暂无机构信息
引用论文
Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey数据驱动的工业设备预测性维护方法综述
.png){kind=icon}
PREAI
分享收藏Introduction to the Special Section on Artificial Intelligence for Next Generation Industrial Cyber-Physical Systems下一代工业网络物理系统人工智能专题介绍
OAAI
OAAI分享收藏
FedCali: Mitigating Overgeneralization for Anomaly Detection in Distributed Sensor Environments
PREAI
分享收藏Weakly Supervised anomaly detection with privacy preservation under a Bi-Level Federated learning framework双层联邦学习框架下具有隐私保护的弱监督异常检测
PREAI
分享收藏
查看更多内容