Séminaire Image : Learning on graphs and hierarchies par Silvio Jamil Ferzoli Guimaraes

Nous aurons le plaisir d’écouter Silvio Jamil Ferzoli Guimaraes, professeur à la Pontifical Catholic University of Minas Gerais.
Il donnera un séminaire IMAGE le jeudi 22 janvier 2026 à 14h en salle de séminaire F-200.

Titre : « Learning on graphs and hierarchies »

Résumé : 

Hierarchies, as described in mathematical morphology, represent nested regions of interest that facilitate high-level analysis and provide mechanisms for coherent data organization. Represented as hierarchical trees, they have formalisms intersecting with graph theory and applications that can be conveniently generalized. However, due to the deterministic algorithms, the multiform representations, and the absence of a direct way to evaluate the hierarchical structure, it is hard to insert hierarchical information into a learning framework and benefit from the recent advances in the field. This work aims to create a learning framework that can operate with hierarchical data and is agnostic to the input and the application. The idea is to study ways to transform the data to a regular representation required by most learning models while preserving the rich information in the hierarchical structure. The methods in this study use edge- weighted image graphs and hierarchical trees as input, evaluating different proposals on the edge detection and segmentation tasks. The model of choice is the Random Forest, a fast, inspectable, scalable method. The experiments demonstrate that it is possible to create a learning framework dependent only on the hierarchical data that performs well in multiple tasks.

Researchers involved in this topic:
Raquel Almeida, Silvio Jamil F. Guimarães, Laurent Amsaleg, Ewa Kijak, Simon Malinowski