Lifelong Representation Learning


Given a set of problems to solve, the dominant paradigm in the AI community has been to solve each problem or task independently. This is in sharp contrast with the human capability to build from past experience and transfer knowledge to speed-up the learning process for a new task. To mimic such a capability, the machine learning community has introduced the concept of continual learning or lifelong learning. The main advantage of this paradigm is that it enables learning with less data, it often allows to learn faster and to generalize better. From an industrial standpoint, the potential of lifelong learning is tremendous as this would mean deploying machine learning models faster by bypassing the need to collect labels.


  • Research and dissemination: see scientific publications
  • Teaching:

"Découvrir l’intelligence artificielle par le jeu"
 (Action développement professionnel de la Maison pour la Science Alpes-Dauphiné).

"Discover AI with games" is a 2-day training session for high school teachers (several sessions organised).

Chair events


  • August 2020. Invited keynote at the Instance-Level Recognition Workshop at ECCV20: "From Instance-Level to Semantic Image Retrieval"
  • October 2020. Invited keynote at the MIAI-DAY 2020: "Learning generic and transferrable visual representations with weak supervision"

Scientific publications

Peer-reviewed publications

Dissemination through blog posts