Login / Signup

Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks.

Gen LuoYiyi ZhouXiaoshuai SunYan WangLiujuan CaoYongjian WuFeiyue HuangRongrong Ji
Published in: CoRR (2022)
Keyphrases
  • lightweight
  • group wise
  • computer vision
  • development environments
  • atlas construction
  • image data
  • rfid tags
  • diffusion tensor images
  • communication infrastructure