DESCRIPTION :
In the context of a collaborative project between Inria Saclay OPIS and SafranTech, the aim of this internship is to investigate generative AI techniques for non-stationary vibration signals, such as those encountereed in aircraft rotor monitoring.
Subject: Recent advances in generative artificial intelligence (AI) have shown remarkable success in the image domain, particularly for high-resolution methods such as diffusion models, flow models, and GANs [1,2]. In this internship, we investigate AI generative techniques to handle non-stationary signals, aiming to develop an AI model for super-resolution of time-frequency (TF) representations.
During this internship, the student will conduct a literature review on TF super-resolution [3], including optimization-based, discriminative, and generative methods. They will implement a AI-based TF super-resolution algorithm, evaluate it on synthetic datasets, and explore potential real-world datasets for application.
The research conducted during this project has the potential to result in a publication in leading conferences on artificial intelligence or signal processing.
[1] Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David
Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gener-
ative adversarial networks, 2014.
[2] Ségolène Martin, Anne Gagneux, Paul Hagemann, and Gabriele Steidl.
Pnp-flow: Plug-and-play image restoration with flow matching, 2025.
[3] Vasile V Moca, Harald Barzan, Adriana Nagy-Dabacan, and Raul C
Mures. Time-frequency super-resolution with superlets. Nature com-
munications, 12(1):337, 2021.
Mission confiée
Missions: Literature review ; Implementation ; Evaluation on public datasets
Environment: The intern will be supervised by Emilie Chouzenoux (Head of OPIS team, Inria Saclay) and Imed Moussa (PhD student, OPIS-SafranTech). The intern student will join the Inria Saclay team OPIS (https://opis-inria.eu/). He/she will be located in the Centre de la Vision Numérique, in CentraleSupélec campus, Saclay, France. He/she will enjoy an international and creative environment where research seminars and reading groups take place very often. Informatic material expenses will be covered within the limits of the scale in force.
Organization: The proposed offer is dedicated to internship of Master 2 students. The starting/end dates
are flexible, with a minimum duration of 5 months.
Principales activités
Main activities :
Programming in Python environment
Bibliographical study
Deep learning architecture design
Scientific meetings
Deep learning training/testing
Writing of scientific reports
Code d'emploi : Stagiaire (h/f)
Niveau de formation : Bac+5
Temps partiel / Temps plein : Plein temps
Type de contrat : Stage/Jeune diplômé
Compétences : Intelligence Artificielle, Programmation Informatique, Python (Langage de Programmation), Machine Learning, Tensorflow, Traitement de Signal, Pytorch, Deep Learning, Generative AI, Anglais, Français, Recherche, Algorithmes, Conception Architecturale, Vibrations, Annuaire International de l'Enseignement Médical, Coûts d'Exploitation, Service d'Information sur le Prix du Pétrole, Réalisation de Tests, Littérature
Courriel :
emilie.chouzenoux@inria.fr
Téléphone :
0139635511
Type d'annonceur : Employeur direct