CORE: Consistent Representation Learning for Face Forgery Detection
This work addresses the issue of detecting manipulated faces, which is important for security and media integrity, but it is incremental as it builds on existing erasing-based augmentation methods.
The paper tackles the problem of face forgery detection by addressing overfitting in convolutional neural networks, proposing a framework called CORE that explicitly regularizes representation consistency across augmentations, which achieves favorable performance against state-of-the-art methods in in-dataset and cross-dataset experiments.
Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer from the overfitting issue. To relieve this issue, there is a trend to introduce some erasing-based augmentations. We find that these methods indeed attempt to implicitly induce more consistent representations for different augmentations via assigning the same label for different augmented images. However, due to the lack of explicit regularization, the consistency between different representations is less satisfactory. Therefore, we constrain the consistency of different representations explicitly and propose a simple yet effective framework, COnsistent REpresentation Learning (CORE). Specifically, we first capture the different representations with different augmentations, then regularize the cosine distance of the representations to enhance the consistency. Extensive experiments (in-dataset and cross-dataset) demonstrate that CORE performs favorably against state-of-the-art face forgery detection methods.