Login / Signup

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers.

Jihao LiuXin HuangJinliang ZhengYu LiuHongsheng Li
Published in: CVPR (2023)
Keyphrases
  • real time
  • computer vision
  • information extraction
  • computationally efficient
  • cost effective
  • computationally expensive
  • real world
  • evolutionary algorithm
  • lightweight
  • coarse to fine
  • highly efficient