Computer Vision Model Compression Techniques for Embedded Systems:A Survey
Computers & Graphics · 2024-10 · 123 · 104015
DOI: 10.1016/j.cag.2024.104015 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers & Graphics, 2024-10. Verfasst von Alexandre Lopes und 4 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 127 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Deep neural networks have consistently represented the state of the art in most computer vision problems. In these scenarios, larger and more complex models have demonstrated superior performance to smaller architectures, especially when trained with plenty of representative data. With the recent adoption of Vision Transformer (ViT) based architectures and advanced Convolutional Neural Networks (CNNs), the total number of parameters of leading backbone architectures increased from 62M parameters in 2012 with AlexNet to 7B parameters in 2024 with AIM-7B. Consequently, deploying such deep architectures faces challenges in environments with processing and runtime constraints, particularly in embedded systems. This paper covers the main model compression techniques applied for computer vision tasks, enabling modern models to be used in embedded systems. We present the characteristics of compression subareas, compare different approaches, and discuss how to choose the best technique and expected variations when analyzing it on various embedded devices. We also share codes to assist researchers and new practitioners in overcoming initial implementation challenges for each subarea and present trends for Model Compression. Case studies for compression models are available at \href{https://github.com/venturusbr/cv-model-compression}{https://github.com/venturusbr/cv-model-compression}.
Zitieren
APA
Lopes, A., Santos, F. P. D., Oliveira, D. D., Schiezaro, M., & Pedrini, H. (2024). Computer Vision Model Compression Techniques for Embedded Systems:A Survey. Computers & Graphics, 123, 104015. https://doi.org/10.1016/j.cag.2024.104015
Vancouver
Lopes A, Santos FPD, Oliveira DD, Schiezaro M, Pedrini H. Computer Vision Model Compression Techniques for Embedded Systems:A Survey. Computers & Graphics. 2024;123:104015. doi:10.1016/j.cag.2024.104015
BibTeX
@article{Lopes2024,
author = {Lopes, Alexandre and Santos, Fernando Pereira dos and Oliveira, Diulhio de and Schiezaro, Mauricio and Pedrini, Helio},
title = {Computer Vision Model Compression Techniques for Embedded Systems:A Survey},
journal = {Computers & Graphics},
year = {2024},
volume = {123},
pages = {104015},
doi = {10.1016/j.cag.2024.104015}
}
EUVIMED