Memeify: A Large-Scale Meme Generation System

TL;DR

Memeify is a large-scale meme generation system that creates memes with captions using a transformer-based model, supported by a comprehensive dataset and a user-friendly web interface for meme creation and evaluation.

Contribution

The paper introduces a large meme dataset with class labels and themes, and develops a transformer-based system with a web interface for meme generation and qualitative evaluation.

Findings

Created a dataset of 1.1 million meme captions across 128 classes

Developed a transformer-based meme caption generation system

Conducted user study for qualitative assessment

Abstract

Interest in the research areas related to meme propagation and generation has been increasing rapidly in the last couple of years. Meme datasets available online are either specific to a context or contain no class information. Here, we prepare a large-scale dataset of memes with captions and class labels. The dataset consists of 1.1 million meme captions from 128 classes. We also provide reasoning for the existence of broad categories, called "themes" across the meme dataset; each theme consists of multiple meme classes. Our generation system uses a trained state-of-the-art transformer-based model for caption generation by employing an encoder-decoder architecture. We develop a web interface, called Memeify for users to generate memes of their choice, and explain in detail, the working of individual components of the system. We also perform a qualitative evaluation of the generated memes by conducting a user study. A link to the demonstration of the Memeify system is https://youtu.be/P_Tfs0X-czs.