Talks and presentations

Vision-language pre-trained models

2024-03-11 at IMT Atlantique, Brest

A talk on vision-language pre-trained models: CLIP and various methods of few-shot adaptation. Record here.

Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning

2023-11-01 at Sony R&D, Stuttgart

A talk on Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning.

Few-shot Learning

2022-05-04 at the French Tech Meetup, Brest.

A talk on FSL, standard pre-training of few-shot models (SSL, Manifold Mixup) and common few-shot adaptation techniques as well as our contribution EASY.