Comprehensive Survey of Model Compression and Speed up for Vision Transformers
Journal of Information, Technology and Policy · 04.04.2024 · 1-12
DOI: 10.62836/jitp.v1i1.156 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Information, Technology and Policy, online erschienen am 04.04.2024. Verfasst von Feiyang Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Vision Transformers (ViT) have marked a paradigm shift in computer vision, outperforming state-of-the-art models across diverse tasks. However, their practical deployment is hampered by high computational and memory demands. This study addresses the challenge by evaluating four primary model compression techniques: quantization, low-rank approximation, knowledge distillation, and pruning. We methodically analyze and compare the efficacy of these techniques and their combinations in optimizing ViTs for resource-constrained environments. Our comprehensive experimental evaluation demonstrates that these methods facilitate a balanced compromise between model accuracy and computational efficiency, paving the way for wider application in edge computing devices.
Zitieren
APA
Chen, F., Luo, Z., Zhou, L., Pan, X., & Jiang, Y. (2024). Comprehensive Survey of Model Compression and Speed up for Vision Transformers. Journal of Information, Technology and Policy, 1-12. https://doi.org/10.62836/jitp.v1i1.156
Vancouver
Chen F, Luo Z, Zhou L, Pan X, Jiang Y. Comprehensive Survey of Model Compression and Speed up for Vision Transformers. Journal of Information, Technology and Policy. 2024:1-12. doi:10.62836/jitp.v1i1.156
BibTeX
@article{Chen2024,
author = {Chen, Feiyang and Luo, Ziqian and Zhou, Lisang and Pan, Xueting and Jiang, Ying},
title = {Comprehensive Survey of Model Compression and Speed up for Vision Transformers},
journal = {Journal of Information, Technology and Policy},
year = {2024},
pages = {1--12},
doi = {10.62836/jitp.v1i1.156}
}
EUVIMED