Recently, various Deepfake detection methods have been proposed, and most of them are based on convolutional neural networks (CNNs). These detection methods suffer from overfitting on the source dataset and do not perform well on cross-domain datasets which have different distributions from the source dataset. To address these limitations, a new method named FeatureTransfer is proposed in this paper, which is a two-stage Deepfake detection method combining with transfer learning. Firstly, The CNN model pretrained on a third-party large-scale Deepfake dataset can be used to extract the more transferable feature vectors of Deepfake videos in the source and target domains. Secondly, these feature vectors are fed into the domain-adversarial neural network based on backpropagation (BP-DANN) for unsupervised domain adaptive training, where the videos in the source domain have real or fake labels, while the videos in the target domain are unlabelled. The experimental results indicate that the proposed method FeatureTransfer can effectively solve the overfitting problem in Deepfake detection and greatly improve the performance of cross-dataset evaluation.

中文翻译：

---

FeatureTransfer：用于跨域 Deepfake 检测的无监督域适应

最近，各种Deepfake检测方法被提出，其中大部分是基于卷积神经网络（CNNs）。这些检测方法在源数据集上存在过度拟合的问题，并且在与源数据集具有不同分布的跨域数据集上表现不佳。为了解决这些限制，本文提出了一种名为 FeatureTransfer 的新方法，这是一种结合迁移学习的两阶段 Deepfake 检测方法。首先，在第三方大规模 Deepfake 数据集上预训练的 CNN 模型可用于提取 Deepfake 视频在源域和目标域中更易迁移的特征向量。其次，将这些特征向量输入基于反向传播（BP-DANN）的域对抗神经网络进行无监督域自适应训练，其中源域中的视频具有真实或虚假的标签，而目标域中的视频未标记。实验结果表明，所提出的方法FeatureTransfer可以有效解决Deepfake检测中的过拟合问题，大大提高了跨数据集评估的性能。