Controllable Guide-Space for Generalizable Face Forgery Detection
This work addresses the domain generalization issue in face forgery detection, which is crucial for real-world security applications, but it appears incremental as it builds on existing methods to improve feature separation.
The paper tackles the problem of poor generalization in face forgery detection across unknown domains by proposing a controllable guide-space method to enhance forgery-relevant feature discrimination, achieving state-of-the-art generalization in cross-domain settings.
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.