Papers › Negative to Positive Co-learning with Aggressive Modality Dropout

Negative to Positive Co-learning with Aggressive Modality Dropout

1 Jan 2025arXiv:2501.00865archive 2025-07-28

Nicholas Magal, Minh Tran, Riku Arakawa, Suzanne Nie

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

PaperPDFCode

Code

nmagal/modality_drop_for_colearning officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DropoutNCL

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections