Hierarchical Knowledge Transfer: Cross-Layer Distillation for Industrial Anomaly Detection

There are two problems with traditional knowledge distillation methods in industrial anomaly detection: first, traditional methods mostly use feature alignment between the same layers. The second is that similar or even identical structures are usually used to build teacher-student models, thus limi...

Cijeli opis

Bibliografski detalji

Glavni autori:	Junning Xu, Sanxin Jiang
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2025-03-01
Serija:	Journal of Imaging
Teme:	anomaly detection knowledge distillation cross-layer transfer attention mechanism feature extraction
Online pristup:	https://www.mdpi.com/2313-433X/11/4/102
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!