Hateful Memes Detection

Take an image, add some text: you’ve got a meme. Internet memes are often harmless and sometimes hilarious. However, by using certain types of images, text, or combinations of each of these data modalities, the seemingly non-hateful meme becomes a multimodal type of hate speech, a hateful meme.

Starter code from Facebook AI’s MMF is also available on GitHub to help you get started.

Facebook AI

The goal is to create an algorithm that identifies multimodal hate speech in internet memes.

Hateful Memes: Phase 1

Hateful Memes: Phase 2

Dataset

Sign-up DRIVEN_DATA to download External data

Models

Pre-trained models

Colab with VM

• Install Goolge Cloud SDK
• Create Deep Learning VM
• Connect Colab to VM

Tutorial

Hateful Memes Challenge tutorial

Team Members

• Yi Gu: ygu308@gatech.edu
• Wenlei Li: wli491@gatech.edu
• Ning Qiao: nqiao6@gatech.edu
• Stephen Wang: stephen.wang@gatech.edu