An Optimized and Accelerated Object Instance Segmentation Model for Low-Power Edge Devices

Diego Bellani, Valerio Venanzi, Shadi Andishmand, Luigi Cinque, Marco Raoul Marini

2025

Abstract

Deep learning, for sustainable applications or in cases of energy scarcity, requires using available, cost-effective, and energy-efficient accelerators together with efficient models. We explore using the Yolact model, for instance, segmentation, running on a low power consumption device (e.g., Intel Neural Computing Stick 2 (NCS2)), to detect and segment-specific objects. We have changed the Feature Pyramid Network (FPN) and pruning techniques to make the model usable for this application. The final model achieves a noticeable result in Frames Per Second (FPS) on the edge device while achieving a consistent mean Average Precision (mAP).

Paper Citation

in Harvard Style

Bellani D., Venanzi V., Andishmand S., Cinque L. and Marini M. (2025). An Optimized and Accelerated Object Instance Segmentation Model for Low-Power Edge Devices. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 485-495. DOI: 10.5220/0013200700003905

in Bibtex Style

@conference{icpram25,
author={Diego Bellani and Valerio Venanzi and Shadi Andishmand and Luigi Cinque and Marco Marini},
title={An Optimized and Accelerated Object Instance Segmentation Model for Low-Power Edge Devices},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={485-495},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013200700003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - An Optimized and Accelerated Object Instance Segmentation Model for Low-Power Edge Devices
SN - 978-989-758-730-6
AU - Bellani D.
AU - Venanzi V.
AU - Andishmand S.
AU - Cinque L.
AU - Marini M.
PY - 2025
SP - 485
EP - 495
DO - 10.5220/0013200700003905
PB - SciTePress