论文标题
野外假脸检测的全球质地增强
Global Texture Enhancement for Fake Face Detection in the Wild
论文作者
论文摘要
生成的对抗网络（GAN）可以产生可容易欺骗人类的逼真的假面图像。相反，一个常见的卷积神经网络（CNN）歧视器可以实现超过99.9％的精确度，以辨别假/真实的图像。在本文中，我们对假/真实面孔进行了实证研究，并有两个重要的观察：首先，假面的质地与真实面孔大不相同。其次，全局纹理统计信息更适合图像编辑，并且可以从不同的gan和数据集中转移到假面。在上述观察结果的推动下，我们提出了一种新的架构，以革兰氏净为单位，该架构利用全球图像纹理表示来进行健壮的假图像检测。几个数据集上的实验结果表明，我们的革兰氏网络的表现优于现有方法。尤其是，我们的革兰氏阴性局更适合图像编辑，例如下采样，JPEG压缩，模糊和噪声。更重要的是，我们的革兰氏网络在检测训练阶段看不见的GAN模型的假面时明显更好地概括了，并且可以在检测假自然图像时表现出色。
Generative Adversarial Networks (GANs) can generate realistic fake face images that can easily fool human beings.On the contrary, a common Convolutional Neural Network(CNN) discriminator can achieve more than 99.9% accuracyin discerning fake/real images. In this paper, we conduct an empirical study on fake/real faces, and have two important observations: firstly, the texture of fake faces is substantially different from real ones; secondly, global texture statistics are more robust to image editing and transferable to fake faces from different GANs and datasets. Motivated by the above observations, we propose a new architecture coined as Gram-Net, which leverages global image texture representations for robust fake image detection. Experimental results on several datasets demonstrate that our Gram-Net outperforms existing approaches. Especially, our Gram-Netis more robust to image editings, e.g. down-sampling, JPEG compression, blur, and noise. More importantly, our Gram-Net generalizes significantly better in detecting fake faces from GAN models not seen in the training phase and can perform decently in detecting fake natural images.
