ICCV · 2023 · Conference paper

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

Hongguang Zhu, Yunchao Wei, Xiaodan Liang, Chunjie Zhang, Yao Zhao

Rendered by arXiv from the LaTeX source. If anything looks wrong, switch to the PDF.HTML · PDF · Open in a new tab ↗ · Close

Published in: IEEE International Conference on Computer Vision
Date: 2023-08-14
Citations: 45
arXiv: 2308.07146 ↗

Cite

@inproceedings{zhu2023ctp,
  title = {CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation},
  author = {Hongguang Zhu and Yunchao Wei and Xiaodan Liang and Chunjie Zhang and Yao Zhao},
  year = {2023},
  booktitle = {IEEE International Conference on Computer Vision},
  eprint = {2308.07146},
  archivePrefix = {arXiv},
  doi = {10.1109/ICCV51070.2023.02034},
  url = {https://arxiv.org/abs/2308.07146},
}