erprogs / CViT

Deepfake Video Detection Using Convolutional Vision Transformer

CViT

Deepfake Video Detection Using Convolutional Vision Transformer

Implementation code for our paper. link to paper | link to MS Thesis | link to MS Thesis defense PPT file

Requirements:

• Pytorch >=1.4

DL library used for face extraction

• helpers_read_video_1.py
• helpers_face_extract_1.py
• blazeface.py
• blazeface.pth

Preprocessing

extractfaces.py
   Face extraction from video.
   The code works for DFDC dataset. You can test it using the sample data provided.

Weights

deepfake_cvit_gpu_ep_50.pth - Full model weight.
deepfake_cvit_gpu_inference_ep_50.pth - For detection.

Predict CViT

python cvit_prediction.py
    Predicts whether a video is Deepfake or not.
    Prediction value <0.5 - REAL
    Prediction value >=5 - FAKE

Train CViT

To train the model on your own you can use the following parameters:
  e: epoch
  s: session - (g) - GPU or (t) - TPU
  w: weight decay default= 0.0000001
  l: learning rate default=0.001
  d: path file
  b: batch size, defualt=32

python cvit_train.py -e 10 -s 'g' -l 0.0001 -w 0.0000001 -d sample_train_data/

Authors

Deressa Wodajo
Solomon Atnafu (PhD)

Bibtex

@misc{wodajo2021deepfake,
      title={Deepfake Video Detection Using Convolutional Vision Transformer}, 
      author={Deressa Wodajo and Solomon Atnafu},
      year={2021},
      eprint={2102.11126},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}