Skip to content

The official code for paper "Can We Leave Deepfake Data Behind in Training Deepfake Detector" (NIPS2024 poster)

Notifications You must be signed in to change notification settings

beautyremain/ProDet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 

Repository files navigation

ProDet

The official code for paper "Can We Leave Deepfake Data Behind in Training Deepfake Detector" (NIPS2024 poster)

main_archi.pdf

ProDet is implemented within the framework of DeepfakeBench. The provided code should be placed in the corresponding folders in DeepfakeBench, and test/train on DeepfakeBench as well. There is no additional package required beyond DeepfakeBench and this repository, hence you should easily reproduce our paper with an established DeepfakeBench environment as:

python training/train.py --detector_path ./training/config/detector/prodet.yaml --train_dataset "FaceForensics++" --test_dataset "FaceForensics++" "Celeb-DF-v2" "DFDCP"

Completely organized code and instructions will be made available soon.

About

The official code for paper "Can We Leave Deepfake Data Behind in Training Deepfake Detector" (NIPS2024 poster)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages