QuantNAS for Super Resolution: Searching for Efficient Quantization-Friendly Architectures Against Quantization Noise

This work aims to develop an automated procedure for discovering new, efficient solutions that can be effectively quantized in mixed-precision mode with minimal degradation. While our primary focus is on Super-Resolution (SR), our proposed procedure is applicable beyond this domain. To achieve our g...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE access 2024, Vol.12, p.117008-117025
Hauptverfasser:	Shvetsov, Egor, Osin, Dmitry, Zaytsev, Alexey, Koryakovskiy, Ivan, Buchnev, Valentin, Trofimov, Ilya, Burnaev, Evgeny
Format:	Artikel
Sprache:	eng
Schlagworte:	Computational modeling Computer architecture Hardware neural architecture search Noise measurement quantization Quantization (signal) regularization Search problems Single image super resolution Superresolution
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!