Exploring Disentangled Content Information for Face Forgery Detection

TL;DR

This paper introduces a disentanglement framework with constraints to improve face forgery detection by reducing content bias and emphasizing artifact traces, leading to more robust performance.

Contribution

It proposes a novel content disentanglement framework with constraints to mitigate content bias in face forgery detection models.

Findings

Framework effectively ignores content interference

Guides detector to focus on artifact traces

Achieves competitive detection performance

Abstract

Convolutional neural network based face forgery detection methods have achieved remarkable results during training, but struggled to maintain comparable performance during testing. We observe that the detector is prone to focus more on content information than artifact traces, suggesting that the detector is sensitive to the intrinsic bias of the dataset, which leads to severe overfitting. Motivated by this key observation, we design an easily embeddable disentanglement framework for content information removal, and further propose a Content Consistency Constraint (C2C) and a Global Representation Contrastive Constraint (GRCC) to enhance the independence of disentangled features. Furthermore, we cleverly construct two unbalanced datasets to investigate the impact of the content bias. Extensive visualizations and experiments demonstrate that our framework can not only ignore the interference of content information, but also guide the detector to mine suspicious artifact traces and achieve competitive performance.