L'invitée du mois : Begüm Demir

50 ans - Keynote IRISA
Date de début
Date de fin
Lieu
IRISA Vannes
Salle
Amphithéâtre Yves Coppens, campus de Tohannic, Vannes
Département principal
Départements supplémentaires

Visuel communication Begüm DEMIR - Guest of the month


As part of its 50th anniversary celebrations, IRISA will welcome leading experts in computer science research throughout 2025 in its "guest of the month" series.

In June, Begüm Demir, Full Professor at BIFOLD and Technische Universität Berlin (Germany), will give a talk on the 6th, in Vannes.


Friday, June 6, 2025
10:00 AM – 11:30 AM

Amphitheater Yves Coppens, campus de Tohannic, Vannes

This talk is open to a non-specialist audience
The conference will be held in English

 

 

🔗 Videoconference link

https://teams.microsoft.com/l/meetup-join/19%3ameeting_MWVjMWZhOTItOTU2Ny00ZTMxLThhMDMtNjE2MWVlZTg0ZGEx%40thread.v2/0?context={"Tid"%3a"2fbd12a9-cbb9-49a2-9612-7af4096a6529"%2c"Oid"%3a"1daf0500-0440-40a3-aa83-0499edc050db"}

 


✍️ Mandatory registration

https://framaforms.org/guest-of-the-month-begum-demir-1744875381

 

 


 

Recent Trends in AI for Earth Observation and Pathways Forward

 

Earth observation (EO) is increasingly used for mapping and monitoring processes occurring at the surface of Earth. Data acquired by satellites nowadays allow us to have a global view, consistent in time, of the state of our forests, oceans, and growing urban areas. However, such a wealth of data has little value without appropriate processing chains able to convert the pixel values to information useful for decision makers.  Recently, machine learning has seen fast advances—especially thanks to the rise of deep learning methodologies—and is increasingly deployed in EO image processing systems. The ever-growing models from computer vision and natural language processing have inspired developments in remote sensing, and new approaches are constantly proposed in the field.

In this talk, our recent developments in the context of artificial intelligence for EO will be presented. Particular attention will be given to our sensor-agnostic learning system defined based on cross-sensor masked autoencoders and its evolvement as an efficient foundation model for EO. We will also shortly present GAIA (which is a global, multi-modal, multi-scale vision-language dataset for EO) and present our recent work on redundancy-aware pretraining of vision-language foundation models. Finally, we will discuss potential pathways for future research.

 



More about Begüm Demir:

Begüm Demir

 


This talk is part of IRISA's 50th anniversary celebrations.
More details about the program on the dedicated page of our website.


Logo des 50 ans de l'IRISA