Analyzing Deep Learning Models’ Generalization Ability Under Different Augmentations on Deepfake Datasets
6th International Conference on Computer Science and Engineering, UBMK 2021, Ankara, Turkey, 15 - 17 September 2021, pp.694-698, (Full Text)
- Publication Type: Conference Paper / Full Text
- Doi Number: 10.1109/ubmk52708.2021.9558927
- City: Ankara
- Country: Turkey
- Page Numbers: pp.694-698
- Keywords: Deepfake, Dfdc, Digital video forensics, Face manipulation
- Yıldız Technical University Affiliated: Yes
Abstract
Deepfakes allow users to manipulate the identity of a person in a video or an image. Improvements on GAN-based techniques also generate more realistic and hard to detect fake faces. This threatens individuals and decreases trust in social media platforms. In this work, our goal is to report eight different models’ learning ability on, by far, the largest fake face dataset - DFDC. The models’ generalization ability was tested on the DFDC test set and Celeb-DF-v2 dataset. Effect of the various cut-out like augmentations to the learning was also reported.