Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes

Understand

This work presents Vilio, an implementation of state-of-the-art visio-linguistic models and their application to the Hateful Memes Dataset.

• The implemented models have been fitted into a uniform code-base and altered to yield better performance.
• The goal of Vilio is to provide a user-friendly starting point for any visio-linguistic problem.
• An ensemble of 5 different V+L models implemented in Vilio achieves 2nd place in the Hateful Memes Challenge out of 3,300 participants.