Dear DFGC-2022 detection track participants,
The second update of the testing data is now available for download under the “Get Data” tab, and the Dev-2 phase will soon begin on April 11, 2022, 1 a.m. UTC.
Please also note that the due date for publishing any new training dataset is approaching, on 2022.4.15. As stated in our rules, to use self-created face swap data (or augmentation) for training or developing models, the dataset must be made publicly available before 2022.4.15 and be explicitly claimed in the competition forum to make other participants aware of this new dataset. Otherwise, these data or augmentation cannot be used in your training process.
Last but not least, we remind participants to strictly abide to the rules. Do not hand-label the released testing dataset for submission or training. Please make sure to carefully read the “Terms and Conditions” page. We will conduct a strict code checking process at the final stage, to ensure reproducibility and abidance to the rules. The participants are responsible to make their training code (and data) easy to be checked and results precisely reproducible. We recommend minimizing as much as possible random factors in your code and using clear and fixed stopping criterions. In case randomness still exists, multiple runs may be conducted.
Best regards,
DFGC organizers.
Posted by: bob_peng @ April 11, 2022, 9:27 a.m.