This paper aims to document an effective way to improve multimodal co-learning by using aggressive modality dropout. We find that by using aggressive modality dropout we are able to reverse negative co-learning (NCL) to positive co-learning (PCL). Aggressive modality dropout can be used to "prep" a multimodal model for unimodal deployment, and dramatically increases model performance during negative co-learning, where during some experiments we saw a 20% gain in accuracy. We also benchmark our modality dropout technique against PCL to show that our modality drop out technique improves co-learning during PCL, although it does not have as much as an substantial effect as it does during NCL. Github: https://github.com/nmagal/modality_drop_for_colearning
Cite
@article{arxiv.2501.00865,
title = {Negative to Positive Co-learning with Aggressive Modality Dropout},
author = {Nicholas Magal and Minh Tran and Riku Arakawa and Suzanne Nie},
journal= {arXiv preprint arXiv:2501.00865},
year = {2025}
}