Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment

Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits or intermediate features, with the aim of producing a well-performed lightweight model. Notably, many subsequent feature...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Yu, Chengting, Zhang, Fengzhao, Chen, Ruizhe, Wang, Aili, Liu, Zuozhu, Tan, Shurun, Li, Er-Ping
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!