"ViT-LSLA: Vision Transformer with Light Self-Limited-Attention."

Zhenzhe Hechen, Wei Huang, Yixin Zhao (2022)

Details and statistics

DOI: 10.48550/ARXIV.2210.17115

access: open

type: Informal or Other Publication

metadata version: 2022-11-03

a service of  Schloss Dagstuhl - Leibniz Center for Informatics