Exploring Intrinsic Dimension for Vision-Language Model Pruning

The intrinsic dimension (ID) represents the minimum dimension needed to describe data on a lower-dimensional manifold within highdimensional spaces. Network pruning aims to reduce the complexity of high-dimensional networks while minimizing performance trade-offs. This symmetry motivates the exploration of ID as a metric for effective pruning. For visionlanguage models, we investigate whether different modalities exist on separate manifolds, indicating varying complexity and prunability. We empirically study ID variations in large-scale visionlanguage pre-trained models and examine the contributions of different modalities to model prunability. We propose a layer importance metric based on ID, which can conveniently integrate with current metrics and enhance performance in vision-language model pruning. The experimental results show a high correlation between ID and modality prunability. Visual representations are more sensitive and crucial to model performance, while language representations are more robust and offer greater prunability. Our findings suggest an asymmetric pruning strategy for vision and language modalities, guided by the ID metric. The code is available at https://github.com/ Nofear18/ID_VL_Pruning