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

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.