AdPE: Adversarial Positional Embeddings for Pretraining Vision Transformers via MAE+.

Xiao Wang Ying Wang Ziwei Xuan Guo-Jun Qi

Published in: CoRR (2023)

Keyphrases

vision system
computer vision
real time
multi agent
low dimensional
vector space
visual perception
computational vision
computational complexity
dimensionality reduction
pattern recognition
data structure
high dimensional data
database systems
manifold learning
image processing
human vision
active vision
database