arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.09903cs.CV
收藏

基于自组织映射的异常检测

Anomaly Detection via Self-organizing Map

Xi'an Jiaotong University(西安交通大学)

Ning Li, Kaitao Jiang, Zhiheng Ma, Xing Wei, Xiaopeng Hong, Yihong Gong

摘要:

异常检测在工业制造中对产品质量控制起着关键作用。传统的异常检测方法是基于规则的,泛化能力有限。最近基于监督深度学习的方法更强大,但需要大规模的注释数据集进行训练。在实践中,异常产品是罕见的,因此,它是非常困难的训练在一个完全监督的方式,一个深模型。本文提出了一种基于自组织映射(SOM)的无监督异常检测方法。我们的方法,自组织映射异常检测(SOMAD)保持正常的特性,使用基于多尺度特征的拓扑记忆。SOMAD在MVTec数据集上实现了无监督异常检测和定位的最新性能。

英文摘要:

Anomaly detection plays a key role in industrial manufacturing for product quality control. Traditional methods for anomaly detection are rule-based with limited generalization ability. Recent methods based on supervised deep learning are more powerful but require large-scale annotated datasets for training. In practice, abnormal products are rare thus it is very difficult to train a deep model in a fully supervised way. In this paper, we propose a novel unsupervised anomaly detection approach based on Self-organizing Map (SOM). Our method, Self-organizing Map for Anomaly Detection (SOMAD) maintains normal characteristics by using topological memory based on multi-scale features. SOMAD achieves state-of the-art performance on unsupervised anomaly detection and localization on the MVTec dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑