/PATAN

Repository for ICCV 2021 paper "Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network"

Primary LanguagePythonMIT LicenseMIT

Partial Adversarial Temporal Attentive Network (PATAN)

This repository is the demo code for the ICCV 2021 paper (oral) "Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network". This repository is built based on the MFNet repository. We thank the authors of MFNet for their excellent work.

alt text

Prerequisites

This repository is built with PyTorch, with the following packages necessary for training and testing:

PyTorch (1.2.0 recommended)
opencv-python (pip)
easydl (pip)

Project Detail and Dataset Download

Please visit our project page to find out details of this work and to download the dataset.

Training and Testing

To train the dataset, simply run:

python train_da.py

Alternatively, you may test with the simple DANN with:

python train_da.py --da-method DANN

To test the dataset, change directory to the '/test' folder and run:

python evaluate_da.py

Notes on training and testing

  • The pretrained model where we start our training from is now uploaded to Gdrive.
  • Notes on the '/exps' folder can be found in the README file in that folder.
  • We provide a demo weight here, you should locate it in the '/exps' folder.

If you find our paper useful, please cite our paper:

@inproceedings{xu2021partial,
  title={Partial video domain adaptation with partial adversarial temporal attentive network},
  author={Xu, Yuecong and Yang, Jianfei and Cao, Haozhi and Chen, Zhenghua and Li, Qi and Mao, Kezhi},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={9332--9341},
  year={2021}
}