Skip to content

[CVPR 2023 Highlight] Official implementation of the paper: "AltFreezing for More General Video Face Forgery Detection"

License

Notifications You must be signed in to change notification settings

ZhendongWang6/AltFreezing

Repository files navigation

AltFreezing for More General Video Face Forgery Detection [CVPR 2023 Highlight 🎉]

Zhendong Wang, Jianmin Bao, Wengang Zhou, Weilun Wang, Houqiang Li

Paper

Abstract

Existing face forgery detection models try to discriminate fake images by detecting only spatial artifacts (e.g., generative artifacts, blending) or mainly temporal artifacts (e.g., flickering, discontinuity). They may experience significant performance degradation when facing out-domain artifacts. In this paper, we propose to capture both spatial and temporal artifacts in one model for face forgery detection. A simple idea is to leverage a spatiotemporal model (3D ConvNet). However, we find that it may easily rely on one type of artifact and ignore the other. To address this issue, we present a novel training strategy called AltFreezing for more general face forgery detection. The AltFreezing aims to encourage the model to detect both spatial and temporal artifacts. It divides the weights of a spatiotemporal network into two groups: spatial-related and temporal-related. Then the two groups of weights are alternately frozen during the training process so that the model can learn spatial and temporal features to distinguish real or fake videos. Furthermore, we introduce various video-level data augmentation methods to improve the generalization capability of the forgery detection model. Extensive experiments show that our framework outperforms existing methods in terms of generalization to unseen manipulations and datasets.

Dependencies

conda create -n altfreezing python=3.9
conda activate altfreezing
pip install torch==1.8.0+cu111 torchvision==0.9.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html
pip install -r requirements.txt

Inference

You can download weights from RecDrive[password: altf] or BaiduDrive[password: altf], and put it into checkpoints. Then run:

python demo.py

Contact

If you have any question, please contact [email protected] or [email protected].

Acknowledgments

Our code is borrowed from FTCN. Thanks for their sharing codes and models.

Citation

@InProceedings{Wang_2023_CVPR,
    author    = {Wang, Zhendong and Bao, Jianmin and Zhou, Wengang and Wang, Weilun and Li, Houqiang},
    title     = {AltFreezing for More General Video Face Forgery Detection},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {4129-4138}
}

About

[CVPR 2023 Highlight] Official implementation of the paper: "AltFreezing for More General Video Face Forgery Detection"

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages