Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality.

Xiang Li Wenhai Wang Lingfeng Yang Jian Yang

Published in: CoRR (2022)

Keyphrases

computer vision
multiscale
vision system
real time
training set
multiresolution
training phase
neural network
training process
support vector
input image
object detection
coarse to fine
training algorithm
linear array
empirically derived