Talk: Fantastic CLIPs and How To Tune Them

Image credit: Unsplash

Abstract

In this talk we explore how to train a CLIP (Contrastive Language-Image Pre-training) for the Italian language and for a Fashion use case. We also explore potential insights given by the language-image capabilities of these models.

Date
Jul 5, 2022 1:00 PM
Event
Invited Talk
Location
Stanford University