论文标题
Defakehop ++：增强的轻量级深泡检测器
DefakeHop++: An Enhanced Lightweight Deepfake Detector
论文作者
论文摘要
在Defakehop的基础上，在这项工作中提出了增强的轻巧的DeepFake检测器，称为DefakeHop ++。这些改进位于两个领域。首先，DeFakehop检查了三个面部区域（即两只眼睛和嘴巴），而Defakehop ++还包括八个范围内的地标，以进行更广泛的覆盖范围。其次，对于判别特征选择，DeFakeHop使用无监督的方法，而DeFakeHop ++采用了一种更有效的方法，可以通过监督，称为判别功能测试（DFT）。在Defakehop ++中，最初是自动衍生自面部区域和地标。然后，DFT用于选择分类器培训的判别功能的子集。与Mobilenet V3（在移动应用程序上针对目标的150万参数的轻量级CNN模型）相比，DeFakeHop ++具有238K参数的模型，这是Mobilenet V3的16％。此外，在弱监督的设置中，Defakehop ++在DeepFake图像检测性能中优于Mobilenet V3。
On the basis of DefakeHop, an enhanced lightweight Deepfake detector called DefakeHop++ is proposed in this work. The improvements lie in two areas. First, DefakeHop examines three facial regions (i.e., two eyes and mouth) while DefakeHop++ includes eight more landmarks for broader coverage. Second, for discriminant features selection, DefakeHop uses an unsupervised approach while DefakeHop++ adopts a more effective approach with supervision, called the Discriminant Feature Test (DFT). In DefakeHop++, rich spatial and spectral features are first derived from facial regions and landmarks automatically. Then, DFT is used to select a subset of discriminant features for classifier training. As compared with MobileNet v3 (a lightweight CNN model of 1.5M parameters targeting at mobile applications), DefakeHop++ has a model of 238K parameters, which is 16% of MobileNet v3. Furthermore, DefakeHop++ outperforms MobileNet v3 in Deepfake image detection performance in a weakly-supervised setting.
