Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?

Diffusion models have recently achieved astonishing performance in generating high-fidelity photo-realistic images. Given their huge success, it is still unclear whether synthetic images are applicable for knowledge distillation when real images are unavailable. In this paper, we extensively study w...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-05
Hauptverfasser:	Li, Zheng, Li, Yuxuan, Zhao, Penghai, Song, Renjie, Li, Xiang, Yang, Jian
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Distillation Synthetic data
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!