Multi-Class Hypersphere Anomaly Detection Based on Edge Outlier Exposure Set and Margin

Min Gao, Xuan Liu, Di Xu and Guowei Yang ()
Additional contact information
Min Gao: School of Computer Science (School of Intelligent Auditing), Nanjing Audit University, Nanjing 211815, China
Xuan Liu: School of Computer Science (School of Intelligent Auditing), Nanjing Audit University, Nanjing 211815, China
Di Xu: School of Computer Science (School of Intelligent Auditing), Nanjing Audit University, Nanjing 211815, China
Guowei Yang: School of Electronic Information, Qingdao University, Qingdao 266071, China

Mathematics, 2024, vol. 12, issue 15, 1-17

Abstract: Currently, the decision boundary of the multi-class anomaly detection algorithm based on deep learning does not sufficiently capture the positive class region, posing a risk of abnormal sample features falling into the domain of normal sample features and potentially leading to misleading outcomes in practical applications. In response to the above problems, this paper proposes a new method called multi-class hypersphere anomaly detection (MMHAD) based on the edge outlier exposure set and margin. The method aims to utilize convolutional neural networks for joint training of all normal object classes, identifying a shared set of outlier exposures, learning compact identification features, and setting appropriate edge parameters to guide the model in mapping outliers outside the hypersphere. This approach enables more comprehensive detection of various types of exceptions. The experiments demonstrate that the algorithm is superior to the most advanced baseline method, with an improvement of 26.0%, 8.2%, and 20.1% on CIFAR-10 and 14.8%, 12.0%, and 20.1% on FMNIST in the cases of (2/8), (5/5), and (9,1), respectively. Furthermore, we investigate the challenging (2/18) case on CIFAR-100, where our method achieves approximately 17.4% AUROC gain. Lastly, for a recycling waste dataset with the (4/1) case, our MMHAD yields a notable 22% enhancement in performance. Experimental results show the effectiveness of the proposed model in multi-classification anomaly detection.

Keywords: deep learning; multi-class anomaly detection; outlier exposure; convolutional neural network (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/15/2340/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/15/2340/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:15:p:2340-:d:1443757

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().