codewithFlycat / DPT

The code of IJCAI2022 paper, Declaration-based Prompt Tuning for Visual Question Answering

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Declaration-based Prompt Tuning for Visual Question Answering

The implementation code of IJCAI 2022 paper: Declaration-based Prompt Tuning for Visual Question Answering.

Requirements

  • Python 3
  • Pytorch>=1.7.1
  • pytorch-transformers==1.2.0

Usage

Declaration Generation

Please follow DeclarationGeneration to set up the experiments for declaration generation.

Visual Question Answering

Please follow VinVL to set up the experiments for visual question answering.

Citation

Please kindly cite our paper if this paper and the code are helpful.

@inproceedings{liu2022dpt,
    author={Liu, Yuhang and Wei, Wei and Peng, Daowan and Zhu, Feida},
    title={Declaration-based Prompt Tuning for Visual Question Answering},
    booktitle={Proceedings of the Thirty-first International Joint Conference on Artificial Intelligence, {IJCAI-22}},
    year={2022}
}

About

The code of IJCAI2022 paper, Declaration-based Prompt Tuning for Visual Question Answering


Languages

Language:Python 99.8%Language:Shell 0.2%