Reference : Profiling the real world potential of neural network compression

	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/52409

Title :	Profiling the real world potential of neural network compression
Language :	English
Author, co-author :	Lorentz, Joe [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Hartmann, Thomas [DataThings S.A.]
	Moawad, Assaad [DataThings S.A.]
	Aouada, Djamila [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2 >]
Publication date :	1-Aug-2022
Main document title :	2022 IEEE International Conference on Omni-layer Intelligent Systems (COINS), Barcelona 1-3 August 2022
Publisher :	IEEE
Peer reviewed :	Yes
ISBN :	978-1-6654-8356-8
Event name :	2022 IEEE International Conference on Omni-layer Intelligent Systems (COINS)
Event date :	from 01.08.2022 to 03.08.2022
Keywords :	[en] machine learning ; computer vision ; model compression
Abstract :	[en] Abstract—Many real world computer vision applications are required to run on hardware with limited computing power, often referred to as ”edge devices”. The state of the art in computer vision continues towards ever bigger and deeper neural networks with equally rising computational requirements. Model compression methods promise to substantially reduce the computation time and memory demands with little to no impact on the model robustness. However, evaluation of the compression is mostly based on theoretic speedups in terms of required floating-point operations. This work offers a tool to profile the actual speedup offered by several compression algorithms. Our results show a significant discrepancy between the theoretical and actual speedup on various hardware setups. Furthermore, we show the potential of model compressions and highlight the importance of selecting the right compression algorithm for a target task and hardware. The code to reproduce our experiments is available at https://hub.datathings.com/papers/2022-coins.
Permalink :	http://hdl.handle.net/10993/52409
DOI :	10.1109/COINS54846.2022.9854973
Mentions required by the publisher for OA :	The final authenticated version is available online at https://doi.ieeecomputersociety.org/10.1109/COINS54846.2022.9854973
FnR project :	FnR ; FNR14297122 > Joe Lorentz > DETECT > Towards Edge-optimized Deep Learning For Explainable Quality Control > 01/01/2020 > 31/12/2023 > 2019

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access Profiling the real world potential of neural network compression-accepted.pdf Author postprint 169.36 kB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map