A Template Is All You Meme

TL;DR

This paper introduces a comprehensive knowledge base of meme templates and demonstrates their effectiveness in improving meme analysis models by enabling better dataset organization and achieving state-of-the-art results.

Contribution

It creates a large meme template knowledge base and develops TSplit, a method for dataset reorganization that enhances model robustness and generalization.

Findings

State-of-the-art performance on multiple datasets

Improved sample efficiency and model robustness

Effective matching of memes to templates using distance-based lookup

Abstract

Templatic memes, characterized by a semantic structure adaptable to the creator's intent, represent a significant yet underexplored area within meme processing literature. With the goal of establishing a new direction for computational meme analysis, here we create a knowledge base composed of more than 5,200 meme templates, information about them, and 54,000 examples of template instances (templatic memes). To investigate the semantic signal of meme templates, we show that we can match memes in datasets to base templates contained in our knowledge base with a distance-based lookup. To demonstrate the power of meme templates, we create TSplit, a method to reorganize datasets, where a template or templatic instance can only appear in either the training or test split. Our re-split datasets enhance general meme knowledge and improve sample efficiency, leading to more robust models. Our examination of meme templates results in state-of-the-art performance for every dataset we consider, paving the way for analysis grounded in templateness.