ORQ-ViT: Outlier resilient Post Training Quantization for vision transformers via outlier decomposition
Journal of Systems Architecture · 2025-11 · 168 · 103530
DOI: 10.1016/j.sysarc.2025.103530 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Systems Architecture, 2025-11. Verfasst von Xinyu He und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Tianjin Municipality, National Natural Science Foundation of China.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Natural Science Foundation of Tianjin Municipality
- National Natural Science Foundation of China
Zitieren
APA
He, X., Lu, Y., Liu, H., Gong, C., & He, W. (2025). ORQ-ViT: Outlier resilient Post Training Quantization for vision transformers via outlier decomposition. Journal of Systems Architecture, 168, 103530. https://doi.org/10.1016/j.sysarc.2025.103530
Vancouver
He X, Lu Y, Liu H, Gong C, He W. ORQ-ViT: Outlier resilient Post Training Quantization for vision transformers via outlier decomposition. Journal of Systems Architecture. 2025;168:103530. doi:10.1016/j.sysarc.2025.103530
BibTeX
@article{He2025,
author = {He, Xinyu and Lu, Ye and Liu, Hang and Gong, Cheng and He, Wenxuan},
title = {ORQ-ViT: Outlier resilient Post Training Quantization for vision transformers via outlier decomposition},
journal = {Journal of Systems Architecture},
year = {2025},
volume = {168},
pages = {103530},
doi = {10.1016/j.sysarc.2025.103530}
}
EUVIMED