无需重训练，插件式模块让人脸伪造检测器在线适应新类型伪造。
Generalize Your Face Forgery Detectors: An Insertable Adaptation Module Is All You Need
- 通过可学习的类别原型分类器，动态融合特征与原型进行判别。
- 在多数据集上优于现有方法，实现更强泛化能力。
- 即插即用，适配多种检测器，适合实际部署场景。
大量人脸伪造检测器被提出以应对深度伪造风险，但其实际应用受限于对训练中未见伪造类型的泛化能力不足。为此，我们提出一种可插入的自适应模块，仅需在线无标签测试数据即可适配已训练好的现成检测器，无需修改架构或训练流程。具体而言，我们设计了一种基于可学习类别原型的分类器，从修正后的特征和原型生成预测，有效处理各类伪造线索与域差异。此外，提出最近特征校准器，提升预测精度并降低自训练中噪声伪标签的影响。跨多个数据集的实验表明，该模块在泛化性能上超越当前最优方法，且作为即插即用组件可与多种检测器结合，显著提升整体表现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。