Journal
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)
Volume -, Issue -, Pages 3769-3778Publisher
IEEE COMPUTER SOC
DOI: 10.1109/ICCVW54120.2021.00421
Keywords
-
Ask authors/readers for more resources
This paper examines the limitations and issues of existing deepfake detection frameworks, identifying the problem of oversampling in deepfake datasets leading to model overfitting. It introduces a data augmentation method called Face-Cutout to enhance data variation and alleviate overfitting. The method shows a significant reduction in LogLoss on various datasets compared to other occlusion-based techniques, and a general-purpose data preprocessing guideline is proposed to enhance the generalizability of models in deepfake detection.
In this paper, we focus on identifying the limitations and shortcomings of existing deepfake detection frameworks. We identified some key problems surrounding deepfake detection through quantitative and qualitative analysis of existing methods and datasets. We found that deepfake datasets are highly oversampled, causing models to become easily overfitted. The datasets are created using a small set of real faces to generate multiple fake samples. When trained on these datasets, models tend to memorize the actors' faces and labels instead of learning fake features. To mitigate this problem, we propose a simple data augmentation method termed Face-Cutout. Our method dynamically cuts out regions of an image using the face landmark information. It helps the model selectively attend to only the relevant regions of the input. Our evaluation experiments show that Face-Cutout can successfully improve the data variation and alleviate the problem of overfitting. Our method achieves a reduction in LogLoss of 15.2% to 35.3% on different datasets, compared to other occlusion-based techniques. Moreover, we also propose a general-purpose data pre-processing guideline to train and evaluate existing architectures allowing us to improve the generalizability of these models for deepfake detection.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available