Improving model robustness against potential modality noise, as an essential step for adapting multimodal models to real-world applications, has received increasing attention among researchers. For Multimodal Sentiment Analysis (MSA), there is also a debate on whether multimodal models are more effective against noisy features than unimodal ones. Stressing on intuitive illustration and in-depth analysis of these concerns, we present Robust-MSA, an interactive platform that visualizes the impact of modality noise as well as simple defence methods to help researchers know better about how their models perform with imperfect real-world data.
@article{arxiv.2211.13484,
title = {Robust-MSA: Understanding the Impact of Modality Noise on Multimodal Sentiment Analysis},
author = {Huisheng Mao and Baozheng Zhang and Hua Xu and Ziqi Yuan and Yihe Liu},
journal= {arXiv preprint arXiv:2211.13484},
year = {2022}
}
Comments
Accept by AAAI 2023. Code is available at https://github.com/thuiar/Robust-MSA