CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Jihai, Qu, Xiaoye, Zhu, Tong, Cheng, Yu
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2409.19291