English

Closing the Modality Gap Aligns Group-Wise Semantics

Machine Learning 2026-01-27 v1 Computer Vision and Pattern Recognition

Abstract

In multimodal learning, CLIP has been recognized as the \textit{de facto} method for learning a shared latent space across multiple modalities, placing similar representations close to each other and moving them away from dissimilar ones. Although CLIP-based losses effectively align modalities at the semantic level, the resulting latent spaces often remain only partially shared, revealing a structural mismatch known as the modality gap. While the necessity of addressing this phenomenon remains debated, particularly given its limited impact on instance-wise tasks (e.g., retrieval), we prove that its influence is instead strongly pronounced in group-level tasks (e.g., clustering). To support this claim, we introduce a novel method designed to consistently reduce this discrepancy in two-modal settings, with a straightforward extension to the general nn-modal case. Through our extensive evaluation, we demonstrate our novel insight: while reducing the gap provides only marginal or inconsistent improvements in traditional instance-wise tasks, it significantly enhances group-wise tasks. These findings may reshape our understanding of the modality gap, highlighting its key role in improving performance on tasks requiring semantic grouping.

Keywords

Cite

@article{arxiv.2601.18525,
  title  = {Closing the Modality Gap Aligns Group-Wise Semantics},
  author = {Eleonora Grassucci and Giordano Cicchetti and Emanuele Frasca and Aurelio Uncini and Danilo Comminiello},
  journal= {arXiv preprint arXiv:2601.18525},
  year   = {2026}
}

Comments

ICLR 2026

R2 v1 2026-07-01T09:20:29.966Z