Attend, Distill, Detect: Attention-aware Entropy Distillation for Anomaly Detection

Unsupervised anomaly detection encompasses diverse applications in industrial settings where a high-throughput and precision is imperative. Early works were centered around one-class-one-model paradigm, which poses significant challenges in large-scale production environments. Knowledge-distillation...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-05
Hauptverfasser:	Jena, Sushovan, Saini, Vishwas, Shaw, Ujjwal, Jain, Pavitra, Abhay Singh Raihal, Banerjee, Anoushka, Joshi, Sharad, Ganesh, Ananth, Bhavsar, Arnav
Format:	Artikel
Sprache:	eng
Schlagworte:	Anomalies Attention Distillation Entropy Feature maps Industrial applications Modules Network latency Teachers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!