Generalize Your Face Forgery Detectors: An Insertable Adaptation Module Is All You Need
This addresses the practical limitation of face forgery detection systems for security applications by enabling better generalization without retraining, though it is incremental as it builds on existing detector frameworks.
The paper tackles the problem of face forgery detectors failing to generalize to unseen forgeries by introducing an insertable adaptation module that adapts trained detectors using only online unlabeled test data, achieving superior generalization across multiple datasets compared to state-of-the-art methods.
A plethora of face forgery detectors exist to tackle facial deepfake risks. However, their practical application is hindered by the challenge of generalizing to forgeries unseen during the training stage. To this end, we introduce an insertable adaptation module that can adapt a trained off-the-shelf detector using only online unlabeled test data, without requiring modifications to the architecture or training process. Specifically, we first present a learnable class prototype-based classifier that generates predictions from the revised features and prototypes, enabling effective handling of various forgery clues and domain gaps during online testing. Additionally, we propose a nearest feature calibrator to further improve prediction accuracy and reduce the impact of noisy pseudo-labels during self-training. Experiments across multiple datasets show that our module achieves superior generalization compared to state-of-the-art methods. Moreover, it functions as a plug-and-play component that can be combined with various detectors to enhance the overall performance.