header image
Home
Romain Raveaux's Home Page
Written by Romain Raveaux   
Jul 18, 2007 at 10:51 PM

Associate Professor (Maître de conférences HDR)

LIFAT computer science laboratory, Université de Tours
(Tours city, France)

 Me

Research activities
  • Image analysis
  • Machine Learning
  • Structural Pattern Recognition
  • Graph matching
  • Graph neural network
  • Discrete optimization
  • Reinforcement learning / Transfert learning


Contact:
Git: https://gitlab.com/romain.raveaux


Romain Raveaux
Université de Tours - LIFAT Research Laboratory, RFAI Group
64 av. Jean Portalis
37200 Tours city, France
Tél : +33 (0)2 47 36 11 59
http://polytech.univ-tours.fr/

A learning graph matching method based on integer linear programming

Goals :
  • An introduction to Learning Graph Matching.
  • The graph matching problem is defined
  • An integer linear program is presented
  • A solver based on the integer linear program is implemented
  • Integration of a combinatorial solver into a deep learning architecture.
  • Backpropagation through a combinatorial solver is presented.
  • An application to key point image matching is proposed.
  • Code in Python base PyTorch Numpy, Matplotlib and Gurobi is proposed through a Jupyter Notebook.
The tutorial can be found here. HTML Notebook

No Graph Matching Solver

With Graph Matching Solver

F2 Method.

Anytime Graph Matching with the ADT method.




Last Updated ( Oct 20, 2023 at 03:54 PM )