Improving Segmentation with Graph Matching

01 Oct 2023 - Rozenn Dahyot

Maynooth University researcher Dr. Jeremy Chopin recently published his PhD work within the journal Computer Vision and Image Understanding DOI:10.1016/j.cviu.2023.103744.

Titled Model-based inexact graph matching on top of DNNs for semantic scene understanding , the work aims to improve 2D and 3D image segmentation performed by deep learning approaches such as CNNs and Transformers by introducting a post-processing step matching a model graph (capturing spatial relationships between regions) with the one found with AI segmentation.

Co-authors include Rozenn Dahyot (Maynooth University), Harold Mouchère (Nantes Université), Jean-Baptiste Fasquel (Université d’Angers), Isabelle Bloch (Sorbonne Université).

Dr. Jeremy Chopin completed his PhD in Angers University (2022) and then joined Maynooth University as part of the SFI research centre ADAPT.