论文标题
学习深层检测的自谐度
Learning Self-Consistency for Deepfake Detection
论文作者
论文摘要
我们提出了一种使用伪造图像中源特征不一致的提示来检测深击图像的新方法。这是基于以下假设：经过最新的深层生成过程后，可以保留和提取图像的不同源特征。我们介绍了一种新颖的表示学习方法，称为Pair-Wise Self-Onesentency学习（PCL），以培训Convnets提取这些源特征并检测深击图像。它伴随着一种新的图像合成方法，称为不一致图像发生器（I2G），为PCL提供丰富注释的训练数据。七个流行数据集的实验结果表明，我们的模型将AUC提高了AUC，从而在数据库评估中从96.45％提高到98.05％，在交叉数据库评估中从86.03％到92.18％。
We propose a new method to detect deepfake images using the cue of the source feature inconsistency within the forged images. It is based on the hypothesis that images' distinct source features can be preserved and extracted after going through state-of-the-art deepfake generation processes. We introduce a novel representation learning approach, called pair-wise self-consistency learning (PCL), for training ConvNets to extract these source features and detect deepfake images. It is accompanied by a new image synthesis approach, called inconsistency image generator (I2G), to provide richly annotated training data for PCL. Experimental results on seven popular datasets show that our models improve averaged AUC over the state of the art from 96.45% to 98.05% in the in-dataset evaluation and from 86.03% to 92.18% in the cross-dataset evaluation.
