ArchiMeDe @ DANKMEMES: A New Model Architecture for Meme Detection

Abstract

English. We introduce ArchiMeDe, a multimodal neural network-based architecture used to solve the DANKMEMES meme detections subtask at the 2020 EVALITA campaign. The system incor-porates information from visual and textual sources through a multimodal neural ensemble to predict if input images and their respective metadata are memes or not. Each pre-trained neural network in the ensemble is first fine-tuned indi-vidually on the training dataset to perform domain adaptation. Learned text and visual representations are then concatenated to obtain a single multimodal embedding