Hello, I'm Eva Feillet.

Welcome on my homepage!

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.

My current research interests include :
- Computer vision
- Continual learning, with focus on class-incremental learning
- Semantic aspects in computer vision
- Resource-efficient training of deep neural networks
- Learning from few data

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

Submitted papers under review.

2024

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

2024

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

[pre-print]

2024

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

[pre-print]

Participation to events

Attended conferences, workshops and seminars.

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 ...