Work

Multi-View Graph Neural Network for Image Segmentation : Intermediate vs Late Fusion

Year: 2025

Type: conference-paper

Abstract: Representing an image as a graph captures its spatial and contextual relationships effectively.Using Graph Neural Networks (GNNs) on graph-based images has considerably enhanced image segmentation.This paper investigates Multi-View GNNs for image segmentation, comparing Intermediate and Late Fusion methods.Experiments show that Intermediate Fusion achieves high accuracy on synthetic data by integrating relational features upfront.On a real dataset, Late Fusion methods, particularly RVCons, outperform Intermediate Fusion by dynamically aggregating multi-view predictions.Indeed, Late Fusion effectively mitigates issues arising from view-specific noise and variance.The results underscore the complementary strengths of both fusion strategies.

Source: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)

DOI: 10.14428/esann/2025.es2025-62

Authors: Elie Karam, Nisrine JRAD, Patty Coupeau, Doron Tobiano, Jean-Baptiste Fasquel, Fahed Abdallah

Institutions: Université catholique de l'ouest, Université d'Angers, Lebanese University, Laboratoire de Conception, Optimisation et Modélisation des Systèmes, Université de Lorraine

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

OpenAlex ID: W4409480881

FWCI:

Cites:

Cited by:

Related to: 10