REVIEW 1 cited by
Negative to Positive Co-learning with Aggressive Modality Dropout
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Negative to Positive Co-learning with Aggressive Modality Dropout
read the original abstract
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
Forward citations
Cited by 1 Pith paper
-
MSNN-LINet: Cross-Modal Learning via Continuous Linear Integration
LINet achieves 45.2% mean class accuracy on SUN RGB-D 19-class scene classification from scratch using continuous linear integration across dedicated RGB, depth, and integration streams.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.