Unimodal Augmentation-based SSL Objectives Induce Cross-Modal Alignment
Zohar Mashiah, Nir Ben-Ari, Ronen Talmon, Uri Shaham
Abstract
Recent works have observed implicit cross-modal alignment between independently trained unimodal models. However, the mechanisms underlying the emergence of this phenomenon remain unresolved. In this paper, we demonstrate that unimodal augmentation-based self-supervised objectives implicitly induce cross-modal alignment. We show that low unimodal losses force high cross-modal alignment, whereas a high unimodal loss prevents such alignment. We theoretically connect the widely used InfoNCE loss to local CKA, the popular measure of cross-modal alignment. We further provide extensive empirical evidence supporting this claim, both in controlled settings and across 53 unconstrained frozen text, vision, and audio unimodal encoders. In both cases, unimodal augmentation-based objectives control cross-modal alignment. Overall, our results provide a theoretical and empirical foundation for understanding the emergence of implicit cross-modal alignment by establishing a direct connection between unimodal training objectives and cross-modal structure.
Create a lesson
Related papers
Coarse Semantic Blocks for Efficient Training-Free Sparse Attention
Sosuke Kobayashi, Shoichiro Yamaguchi, Seiya Tokui
What Is the Influence of Task Order in Continual Learning? An Empirical Study and Order-Aware Evaluation for Motion Forecasting
Zirui Li, Yunlong Lin, Haohan Yang et al.
Reciprocity Can Erase Direction:tructural Boundaries and Controlled Utility of Magnetic Graph Networks
Dawei Han, Zicheng Wang, Yaoxing Ren et al.
Deep Learning Compilers: Architecture, Optimization, and Empirical Characterization
Jinghao Wen, Ruixuan Wang, Xun Jiao
OmniST: Topology-Invariant Spatiotemporal Forecasting with Guaranteed-Coverage Uncertainty at Unseen Sensor Locations
Praveg Vashishtha
LIRA: A More Interpretable Dynamic Loss-Informed Rank Allocation for Low-Rank Adaptation
Sihao Wang, Bozheng Li, Xuemiao Xu et al.