AI RESEARCH
Harmonized Tabular-Image Fusion via Gradient-Aligned Alternating Learning
arXiv CS.CV
•
ArXi:2604.01579v1 Announce Type: new Multimodal tabular-image fusion is an emerging task that has received increasing attention in various domains. However, existing methods may be hindered by gradient conflicts between modalities, misleading the optimization of the unimodal learner. In this paper, we propose a novel Gradient-Aligned Alternating Learning (GAAL) paradigm to address this issue by aligning modality gradients. Specifically, GAAL adopts an alternating unimodal learning and shared classifier to decouple the multimodal gradient and facilitate interaction.