Home

Awesome

Prevalent: A Pretrained Generic VLN Agent

This repository contains source code to reproduce the results presented in the paper:

Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training, CVPR 2020 <br> Weituo Hao*, Chunyuan Li*, Xiujun Li, Lawrence Carin, Jianfeng Gao

<p align="center"> <img width="460" height="300" src=pretrain_finetune.png> </p>

Pretrain

<p align="center"> <kbd> <img width="600" height="250" src=pre_training_scheme.png> </kbd> </p>

Our collected triplets can be downloaded here

The pretrained model can be downloaded here

R2R

CVDN

HANNA

Citation

If you use this code for your research, please cite our paper:

@article{hao2020prevalent,
  title={Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training},
  author={Hao, Weituo and Li, Chunyuan and Li, Xiujun and Carin, Lawrence and Gao, Jianfeng},
  journal={Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020}
}