Detecting Hateful Memes Using a Multimodal Deep Ensemble
Machine Learning
2020-12-25 v1 Computation and Language
Computer Vision and Pattern Recognition
Abstract
While significant progress has been made using machine learning algorithms to detect hate speech, important technical challenges still remain to be solved in order to bring their performance closer to human accuracy. We investigate several of the most recent visual-linguistic Transformer architectures and propose improvements to increase their performance for this task. The proposed model outperforms the baselines by a large margin and ranks 5 on the leaderboard out of 3,100+ participants.
Cite
@article{arxiv.2012.13235,
title = {Detecting Hateful Memes Using a Multimodal Deep Ensemble},
author = {Vlad Sandulescu},
journal= {arXiv preprint arXiv:2012.13235},
year = {2020}
}
Comments
6 pages, NeurIPS 2020, The Hateful Memes Challenge Workshop at NeurIPS 2020