Huang Wei, Li Yongjie, Xu Zhaonan, Yao Xinwei, Wan Rongchun
College of Computer Science, Zhejiang University of Technology, Hangzhou 310023, China.
Zhejiang HOUDAR Intelligent Technology Co., Ltd., Hangzhou 310023, China.
Sensors (Basel). 2024 Dec 26;25(1):67. doi: 10.3390/s25010067.
In industrial contexts, anomaly detection is crucial for ensuring quality control and maintaining operational efficiency in manufacturing processes. Leveraging high-level features extracted from ImageNet-trained networks and the robust capabilities of the Deep Support Vector Data Description (SVDD) model for anomaly detection, this paper proposes an improved Deep SVDD model, termed Feature-Patching SVDD (FPSVDD), designed for unsupervised anomaly detection in industrial applications. This model integrates a feature-patching technique with the Deep SVDD framework. Features are extracted from a pre-trained backbone network on ImageNet, and each extracted feature is split into multiple small patches of appropriate size. This approach effectively captures both macro-structural information and fine-grained local information from the extracted features, enhancing the model's sensitivity to anomalies. The feature patches are then aggregated and concatenated for further training with the Deep SVDD model. Experimental results on both the MvTec AD and CIFAR-10 datasets demonstrate that our model outperforms current mainstream approaches and provides significant improvements in anomaly detection performance, which is vital for industrial quality assurance and defect detection in real-time manufacturing scenarios.
在工业环境中，异常检测对于确保制造过程中的质量控制和维持运营效率至关重要。利用从在ImageNet上训练的网络中提取的高级特征以及深度支持向量数据描述（SVDD）模型用于异常检测的强大功能，本文提出了一种改进的深度SVDD模型，称为特征修补SVDD（FPSVDD），专为工业应用中的无监督异常检测而设计。该模型将特征修补技术与深度SVDD框架相结合。特征是从在ImageNet上预训练的主干网络中提取的，并且每个提取的特征被分割成多个大小合适的小补丁。这种方法有效地从提取的特征中捕获宏观结构信息和细粒度的局部信息，提高了模型对异常的敏感性。然后将特征补丁聚合并连接起来，以便与深度SVDD模型进行进一步训练。在MvTec AD和CIFAR-10数据集上的实验结果表明，我们的模型优于当前的主流方法，并在异常检测性能方面有显著提升，这对于工业质量保证和实时制造场景中的缺陷检测至关重要。
