The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Code

• github.com/facebookresearch/mmf
  OfficialIn paperpytorch★ 5,624
• github.com/rizavelioglu/hateful_memes-hate_detectron
  none★ 61
• github.com/holman57/Hateful-Memes
  pytorch★ 2
• github.com/SebKleiner/Hateful_Memes
  none★ 0

Abstract

This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples ("benign confounders") are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art methods perform poorly compared to humans (64.73% vs. 84.7% accuracy), illustrating the difficulty of the task and highlighting the challenge that this important problem poses to the community.

Tasks

Benchmark Results

Reproductions