AI RESEARCH
Adaptive MLP Pruning for Large Vision Transformers
arXiv CS.CV
•
ArXi:2603.08100v1 Announce Type: new Large vision transformers present impressive scalability, as their performance can be well improved with increased model capacity. Nevertheless, their cumbersome parameters results in exorbitant computational and memory demands. By analyzing prevalent transformer structures, we find that multilayer perceptron (MLP) modules constitute the largest share of the model's parameters. In this paper, we propose an Adaptive MLP Pruning (AMP) method to substantially reduce the parameters of large vision transformers without obvious performance degradation.