Re-M3Dr is a multimodal regression framework using adaptive-margin supervised contrastive learning and sharpness-aware gradient modulation to stabilize training and reduce MSE by 29% versus SOTA multimodal methods on clinical eye-imaging datasets for mean deviation prediction.
Balancebench- mark: A survey for multimodal imbalance learning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
BMLR reshapes the cross-modal label space to equalize mapping difficulty and balance optimization across modalities in multimodal learning.
citing papers explorer
-
Re-M3Dr: Rebalanced MultiModal Mean Deviation Regression
Re-M3Dr is a multimodal regression framework using adaptive-margin supervised contrastive learning and sharpness-aware gradient modulation to stabilize training and reduce MSE by 29% versus SOTA multimodal methods on clinical eye-imaging datasets for mean deviation prediction.
-
Balancing Multimodal Learning through Label Space Reshaping
BMLR reshapes the cross-modal label space to equalize mapping difficulty and balance optimization across modalities in multimodal learning.