Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Dieter Balemans 1 ; 2 ; Benjamin Vandersmissen 3 ; Jan Steckel 2 ; Siegfried Mercelis 1 ; Phil Reiter 3 and José Oramas 3

Affiliations: 1 Faculty of Applied Engineering, University of Antwerp - imec - IDLab, Sint-Pietersvliet 7, 2000 Antwerp, Belgium ; 2 Faculty of Applied Engineering, University of Antwerp - CoSysLab, Groenenborgerlaan 171, 2020 Antwerp, Belgium ; 3 Faculty of Science, University of Antwerp - imec - IDLab, Sint-Pietersvliet 7, 2000 Antwerp, Belgium

Keyword(s): Activity Recognition, Model Compression, Pruning, Quantization, Edge Computing.

Abstract: This paper presents an approach to adapt an existing activity recognition model for efficient deployment on edge devices. The used model, called YOWO (You Only Watch Once), is a prominent deep learning model. Given its computational complexity, direct deployment on resource-constrained edge devices is challenging. To address this, we propose a two-stage compression methodology consisting of structured channel pruning and quantization. The goal is to significantly reduce the model’s size and computational needs while maintaining acceptable task performance. Our experimental results, obtained by deploying the compressed model on Raspberry Pi 4 Model B, confirm that our approach effectively reduces the model’s size and operations while maintaining satisfactory performance. This study paves the way for efficient activity recognition on edge devices.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.137.153.39

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Balemans, D., Vandersmissen, B., Steckel, J., Mercelis, S., Reiter, P. and Oramas, J. (2024). Deep Learning Model Compression for Resource Efficient Activity Recognition on Edge Devices: A Case Study. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP; ISBN 978-989-758-679-8; ISSN 2184-4321, SciTePress, pages 575-584. DOI: 10.5220/0012423300003660

@conference{visapp24,
author={Dieter Balemans and Benjamin Vandersmissen and Jan Steckel and Siegfried Mercelis and Phil Reiter and José Oramas},
title={Deep Learning Model Compression for Resource Efficient Activity Recognition on Edge Devices: A Case Study},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP},
year={2024},
pages={575-584},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012423300003660},
isbn={978-989-758-679-8},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP
TI - Deep Learning Model Compression for Resource Efficient Activity Recognition on Edge Devices: A Case Study
SN - 978-989-758-679-8
IS - 2184-4321
AU - Balemans, D.
AU - Vandersmissen, B.
AU - Steckel, J.
AU - Mercelis, S.
AU - Reiter, P.
AU - Oramas, J.
PY - 2024
SP - 575
EP - 584
DO - 10.5220/0012423300003660
PB - SciTePress