Login / Signup

CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation.

Hongguang ZhuYunchao WeiXiaodan LiangChunjie ZhangYao Zhao
Published in: ICCV (2023)
Keyphrases
  • topology preservation
  • topology preserving
  • parallel thinning algorithm
  • vision system
  • computer vision
  • self organizing maps
  • binary images
  • machine learning
  • texture features
  • thinning algorithm