About me
Education
I am a PhD researcher in Machine Learning and Computer Vision. I conducted my research in the CEA LIST of CEA Tech and in the IMAGINE team of Ecole des Ponts Paristech in Paris. My works are focusing on Exemplar-Free Class-Incremental Learning problems, which aims at learning new classes while keeping the knowledge of the previous ones. During my PhD studies, I was supervised by Dr. Adrian Popescu, Dr. Bertrand Delezoide and Prof. David Picard. My thesis was funded by AI4Media, a 4-year-long project funded under the European Unionâs Horizon 2020 research and innovation programme.
I graduated from IMT Atlantique with a Master of Engineering in Information Technology (Telecom Bretagne) and from the Georgia Institute of Technology with a Master of Science in Computer Science, specializing in Machine Learning.
News
- January 2024: I presented my work on PreTrIL at the WACV2024 conference in Waikoloa, HI, USA.
- I defended my PhD. on the 5th of December 2023!
- August 2023: I presented my work on PlaStIL at the CoLLAs2023 conference in Montréal, Canada.
- January 2023: I presented my work on FeTrIL at the WACV2023 conference in Waikoloa, HI, USA.
- September 2022: I attended the AI4Media colloquium in Thessaloniki, Greece.
- July 2022: I participated in the VISUM summer school in Porto, Portugal.
- June 2022: I attended the CVPR2022 in New Orleans, LA, USA.
Publications
Below are listed my publications, from the latest to the oldest. You can also find my articles on my Google Scholar profile.
An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning
Authors: Grégoire Petit, Michael Soumm, Eva Feillet, Adrian Popescu, Bertrand Delezoide, David Picard and Céline Hudelot
Published in Winter Conference on Applications of Computer Vision (WACV), 2024
PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning
Authors: Grégoire Petit, Adrian Popescu, Eden Belouadah, David Picard and Bertrand Delezoide
Published in Second Conference on Lifelong Learning Agents, 2023
FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
Authors: Grégoire Petit, Adrian Popescu, Hugo Schindler, David Picard and Bertrand Delezoide
Published in Winter Conference on Applications of Computer Vision (WACV), 2023
AdvisIL: A Class-Incremental Learning Advisor
Authors: Eva Feillet, Grégoire Petit, Adrian Popescu, Marina Reyboz and Céline Hudelot
Published in Winter Conference on Applications of Computer Vision (WACV), 2023