Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart

Quantization-aware training (QAT) is a common paradigm for network quantization, in which the training phase incorporates the simulation of the low-precision computation to optimize the quantization parameters in alignment with the task goals. However, direct training of low-precision networks gener...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-12
Hauptverfasser:	Yu, Chengting, Yang, Shu, Zhang, Fengzhao, Ma, Hanzhi, Wang, Aili, Er-Ping, Li
Format:	Artikel
Sprache:	eng
Schlagworte:	Representations
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!