Data Remixing improves multimodal learning by decoupling samples into per-modality subsets and training each batch on a single modality, yielding accuracy gains on CREMAD and Kinetic-Sounds.
On uni-modal feature learning in supervised multi-modal learning
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
-
Improving Multimodal Learning Balance and Sufficiency through Data Remixing
Data Remixing improves multimodal learning by decoupling samples into per-modality subsets and training each batch on a single modality, yielding accuracy gains on CREMAD and Kinetic-Sounds.