SURE reconstructs missing modalities in the latent space of frozen pretrained multimodal models and uses a Pearson-correlation loss plus error propagation to output uncertainty estimates that track prediction error.
Towards robust multimodal prompting with missing modalities
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Are you SURE? Enhancing Multimodal Pretraining with Missing Modalities through Uncertainty Estimation
SURE reconstructs missing modalities in the latent space of frozen pretrained multimodal models and uses a Pearson-correlation loss plus error propagation to output uncertainty estimates that track prediction error.