It's All in the Head: Representation Knowledge Distillation through Classifier Sharing

Representation knowledge distillation aims at transferring rich information from one model to another. Common approaches for representation distillation mainly focus on the direct minimization of distance metrics between the models' embedding vectors. Such direct methods may be limited in trans...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Ben-Baruch, Emanuel, Karklinsky, Matan, Biton, Yossi, Ben-Cohen, Avi, Lawen, Hussam, Zamir, Nadav
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!