English

Enhance Multimodal Model Performance with Data Augmentation: Facebook Hateful Meme Challenge Solution

Machine Learning 2021-06-23 v2 Computers and Society

Abstract

Hateful content detection is one of the areas where deep learning can and should make a significant difference. The Hateful Memes Challenge from Facebook helps fulfill such potential by challenging the contestants to detect hateful speech in multi-modal memes using deep learning algorithms. In this paper, we utilize multi-modal, pre-trained models VilBERT and Visual BERT. We improved models' performance by adding training datasets generated from data augmentation. Enlarging the training data set helped us get a more than 2% boost in terms of AUROC with the Visual BERT model. Our approach achieved 0.7439 AUROC along with an accuracy of 0.7037 on the challenge's test set, which revealed remarkable progress.

Keywords

Cite

@article{arxiv.2105.13132,
  title  = {Enhance Multimodal Model Performance with Data Augmentation: Facebook Hateful Meme Challenge Solution},
  author = {Yang Li and Zinc Zhang and Hutchin Huang},
  journal= {arXiv preprint arXiv:2105.13132},
  year   = {2021}
}

Comments

Our code is available at: https://github.com/yangland/hatefulchallenge

R2 v1 2026-06-24T02:31:40.422Z