Hello, I'm Eva Feillet.

I am a PhD candidate in Frugal Continual Learning at CEA-list / CentraleSupélec MICS in Paris area, France. I am working under the supervision of Dr. Adrian Popescu (CEA-list), Dr. Marina Reyboz (CEA-list) and Pr. Céline Hudelot (CentraleSupélec MICS).
I hold an engineering degree from CentraleSupélec Engineering school (M.Sc. in AI).

My previous work experiences include a research internship on Federated Learning at CEA list in France, and data science internships at IBM Research & Development in Germany and CA-CIB data lab in Singapore.

I am currently looking for a postdoc position. My current research interests include :
- Visual representation learning
- Continual learning
- Semantic aspects in computer vision
- Resource-efficient training of deep neural networks
- Learning from few data

Upcoming PhD defense: December 9th 2024, stay tuned !

Contact me via LinkedIn LinkedIn

Visit my profile on GitHub Github and Google Scholar Scholar

Learn more about my work

Publications

Contributions made during my PhD.

WACV 2024

Feillet, E., Petit, G., Soumm M., Popescu, Delezoïde, B., Picard, D., & Hudelot, C.
An Analysis of Initial Traning Strategies for Exemplar-free Class-Incremental Learning.

In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2024. p. 1837-1847.

[paper] [supp]

WACV 2023

Feillet, E., Petit, G., Popescu, A., Reyboz, M., & Hudelot, C.
AdvisIL - A Class-Incremental Learning Advisor.

In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2023. p. 2400-2409.

[paper] [supp] [code]

RFIAP 2022

Feillet, E., Petit, G., Popescu, A., Reyboz, M., & Hudelot, C.
Incremental Learning under Memory Constraints: a scaling heuristic for deep convolutional models.

In : Reconnaissance des Formes, Image, Apprentissage et Perception. 2022.

[paper] [code]

Pre-prints

Papers to appear shortly.

ICPR 2024

Feillet, E., Popescu, A., & Hudelot, C.
Recommendation of data-free class-incremental learning algorithms by simulating future data.

[pre-print]

To appear in the Proceedings of the International Conference on Pattern Recognition (December 2024)

WACV 2025

Feillet, E., Popescu, A., & Hudelot, C.
A reality check on pre-training for exemplar-free class-incremental learning

To appear in the Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (February 2025)

WACV 2025

Pegeot, T., Feillet, E., Popescu, A., Kucher I., & Delezoïde B.
Temporal Dynamics in Visual Data: Analyzing the Impact of Time on Classification Accuracy

To appear in the Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (February 2025)

Teaching

I have been a teaching assistant for the following courses:
- Deep learning course (Master 2), taught by Hervé Le Borgne at CentraleSupélec
- Information systems and Programming (L3/Bachelor), taught by Gianluca Quercini at CentraleSupélec

Participation to events

Attended conferences, workshops and seminars

HyCHA 2024

Journées d'Intelligence Artificielle Hybride.
Gif-sur-Yvette (France), March 2024

PFIA 2023

Plate-Forme Intelligence Artificielle.
Strasbourg (France), July 2023

WACV 2023

Winter Conference on Applications of Computer Vision.
Waikoloa (USA), January 2023

JRAF 2022

Journées pour la Recherche en Apprentissage Frugal.
Grenoble (France), November 2022

GRETSI Summer School 2022

Summer school on current challenges of Deep Learning.
Peyresq (France), June 2022

RFIAP 2022

Reconnaissance de formes, Images, Apprentissage et Perception.
Vannes (France), June 2022

JDSE 2021

Junior Conference on Data Science and Engineering.
Gif-sur-Yvette (France), September 2021.
Best student paper.

Available projects and repositories

Visit my GitHub account

Get in touch

Send me an email at name.surname@cea.fr or find me on social media.

Find me on ...