Data
If you want to participate to this benchmark, you can download the benchmark images for the binary classification task here.
Documentation
Submission Policy
The videos of the FaceForensics and FaceForensics++ dataset releases may be used for learning the parameters of the algorithms. The test data should be used strictly for reporting the final results -- this benchmark is not meant for iterative testing sessions or parameter tweaking.
Parameter tuning is only allowed on the training data. Evaluating on the test data via this evaluation server must only be done once for the final system. It is not permitted to use it to train systems, for example by trying out different parameter values and choosing the best. Only one version must be evaluated (which performed best on the training data). This is to avoid overfitting on the test data. Results of different parameter settings of an algorithm can therefore only be reported on the training set. To help enforcing this policy, we block updates to the test set results of a method for two weeks after a test set submission. You can split up the training data into training and validation sets yourself as you wish.
It is not permitted to register on this webpage with multiple e-mail addresses. We will ban users or domains if required.
General Info
Code page: Detailed information about our dataset and file formats is provided on our github page, please see our git repo.
Download FaceForensics, FaceForensics++ or DeepFakesDetection: If you would like to download the public FaceForensics, FaceForensics++ or the DeepFakesDetection dataset (for training purposes), please accept the FaceForensics TOS using this google form.
Submission Format
Results for a method must be uploaded as a single .zip or .7z file, which when unzipped must contain a single .json file containing a dictionary of your predicted labels for all benchmark images. With other words: There must not be any additional files or folders in the archive except those specified below. For each image filename the dictionary in the json file should contain one of the two labels "fake" and "real".
You can find a sample submission file here.