GIFF: Graph Iterative Attention Based Feature Fusion for Collaborative Perception

Ahmed N. Ahmed, Siegfried Mercelis, Ali Anwar

2025

Abstract

Multi-agent collaborative perception has gained significant attention due to its ability to overcome the challenges stemming from the limited line-of-sight visibility of individual agents that raised safety concerns for autonomous navigation. This paper introduces GIFF, a graph-based iterative attention collaborative perception framework designed to improve situational awareness among multi-agent systems, including vehicles and roadside units. GIFF enhances autonomous driving perception by fusing perceptual data shared among neighboring agents, allowing agents to “see” through occlusions, detect distant objects, and increase resilience to sensor noise and failures, at low computational cost. To achieve this, we propose a novel framework that integrates both channel and spatial attention mechanisms, learned iteratively and in parallel. We evaluate our approach on object detection task using the V2X-Sim and OPV2V datasets by conducting extensive experiments. GIFF has demonstrated effectiveness compared to state-of-the-art methods and has proved to achieve notable improvements in average precision and the number of model parameters.

Paper Citation

in Harvard Style

Ahmed A., Mercelis S. and Anwar A. (2025). GIFF: Graph Iterative Attention Based Feature Fusion for Collaborative Perception. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 820-829. DOI: 10.5220/0013297900003912

in Bibtex Style

@conference{visapp25,
author={Ahmed Ahmed and Siegfried Mercelis and Ali Anwar},
title={GIFF: Graph Iterative Attention Based Feature Fusion for Collaborative Perception},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={820-829},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013297900003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - GIFF: Graph Iterative Attention Based Feature Fusion for Collaborative Perception
SN - 978-989-758-728-3
AU - Ahmed A.
AU - Mercelis S.
AU - Anwar A.
PY - 2025
SP - 820
EP - 829
DO - 10.5220/0013297900003912
PB - SciTePress