MTHM: Self-supervised Multi-task Anomaly Detection with Hard Example Mining

It is still challenging to detect and locate anomalies by models trained only with normal samples. Methods using image reconstruction as a pretext task can provide precise localization but suffer from harnessing the reconstruction capability on unseen anomalies. This paper proposes a new framework o...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on instrumentation and measurement 2023-05, p.1-1
Hauptverfasser:	Zhang, Chenkai, Wang, Yueming, Tan, Wenming
Format:	Artikel
Sprache:	eng
Schlagworte:	Anomaly detection anomaly localization Data models defect detection Feature extraction Image reconstruction multi-task learning Multitasking Task analysis Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!