"DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions."

Haochen Wang et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2309.03576

access: open

type: Informal or Other Publication

metadata version: 2024-03-26

a service of  Schloss Dagstuhl - Leibniz Center for Informatics