Deep Learning Model Compression for Resource Efficient Activity Recognition on Edge Devices: A Case Study

Dieter Balemans, Dieter Balemans, Benjamin Vandersmissen, Jan Steckel, Siegfried Mercelis, Phil Reiter, José Oramas

2024

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.

Paper Citation

in Harvard Style

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, SciTePress, pages 575-584. DOI: 10.5220/0012423300003660

in Bibtex Style

@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},
}

in EndNote Style

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
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