Controllable Guide-Space for Generalizable Face Forgery Detection

TL;DR

This paper introduces a controllable guide-space method to improve face forgery detection by enhancing domain discrimination and reducing irrelevant information, leading to better cross-domain generalization.

Contribution

The proposed guide-space explicitly separates forgery domains and weakens irrelevant correlations, advancing the generalization capability of face forgery detection methods.

Findings

Achieves state-of-the-art cross-domain detection performance

Effectively separates forgery domains in feature space

Reduces interference from forgery-irrelevant information

Abstract

Recent studies on face forgery detection have shown satisfactory performance for methods involved in training datasets, but are not ideal enough for unknown domains. This motivates many works to improve the generalization, but forgery-irrelevant information, such as image background and identity, still exists in different domain features and causes unexpected clustering, limiting the generalization. In this paper, we propose a controllable guide-space (GS) method to enhance the discrimination of different forgery domains, so as to increase the forgery relevance of features and thereby improve the generalization. The well-designed guide-space can simultaneously achieve both the proper separation of forgery domains and the large distance between real-forgery domains in an explicit and controllable manner. Moreover, for better discrimination, we use a decoupling module to weaken the interference of forgery-irrelevant correlations between domains. Furthermore, we make adjustments to the decision boundary manifold according to the clustering degree of the same domain features within the neighborhood. Extensive experiments in multiple in-domain and cross-domain settings confirm that our method can achieve state-of-the-art generalization.