MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Haokun, Bai, Haoli, Liu, Zhili, Hou, Lu, Sun, Muyi, Song, Linqi, Wei, Ying, Sun, Zhenan
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2403.07839