A lightweight estimator quantifies sample-level multimodal interactions (redundancy, uniqueness, synergy) in continuous distributions and uses them for data partitioning, distillation, and ensembling.
The specific model variant employed in our experiments features unimodal branches, each consisting of four Transformer layers
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
-
Efficient Quantification of Multimodal Interaction at Sample Level
A lightweight estimator quantifies sample-level multimodal interactions (redundancy, uniqueness, synergy) in continuous distributions and uses them for data partitioning, distillation, and ensembling.