English

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

Artificial Intelligence 2020-12-15 v1 Computation and Language Computer Vision and Pattern Recognition

Abstract

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. The code is available at https://github.com/Muennighoff/vilio.

Keywords

Cite

@article{arxiv.2012.07788,
  title  = {Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes},
  author = {Niklas Muennighoff},
  journal= {arXiv preprint arXiv:2012.07788},
  year   = {2020}
}

Comments

Presented at NIPS 2020