Efficient visual transformer transferring from neural ODE perspective

Abstract Recently, the Visual Image Transformer (ViT) has revolutionized various domains in computer vision. The transfer of pre‐trained ViT models on large‐scale datasets has proven to be a promising method for downstream tasks. However, traditional transfer methods introduce numerous additional pa...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao Niu, Fengming Luo, Bo Yuan, Yi Zhang, Jianyong Wang
Format: Article
Language:English
Published: Wiley 2024-09-01
Series:Electronics Letters
Subjects:
Online Access:https://doi.org/10.1049/ell2.70015
Tags: Add Tag
No Tags, Be the first to tag this record!