The highly realistic image quality achieved by current image generative models has many academic and industrial applications. To limit the use of such models to benign applications, though, it is necessary that tools to conclusively detect whether an image has been generated synthetically or not are developed. For this reason, several detectors have been developed providing excellent performance in computer vision applications, however, they can not be applied as they are to multispectral satellite images, and hence new models must be trained. In general, two-class classifiers can achieve very good detection accuracies, however they are not able to generalise to image domains and generative models architectures different than those used during training. For this reason, in this paper, we propose a one-class classifier based on Vector Quantized Variational Autoencoder 2 (VQ-VAE 2) features to overcome the limitations of two-class classifiers. First, we emphasize the generalization problem that binary classifiers suffer from by training and testing an EfficientNet-B4 architecture on multiple multispectral datasets. Then we show that, since the VQ-VAE 2 based classifier is trained only on pristine images, it is able to detect images belonging to different domains and generated by architectures that have not been used during training. Last, we compare the two classifiers head-to-head on the same generated datasets, highlighting the superiori generalization capabilities of the VQ-VAE 2-based detector.

翻译：当前图像生成模型所达到的高度逼真的图像质量具有许多学术和工业应用。然而，为了将此类模型仅用于良性应用，有必要开发能够明确检测图像是否为合成生成的工具。因此，已有多种检测器在计算机视觉应用中表现出色，但它们无法直接应用于多光谱卫星图像，因此需要训练新的模型。通常，二类分类器能够实现非常高的检测精度，但无法泛化到与训练时不同的图像域和生成模型架构。为此，本文提出了一种基于向量量化变分自编码器2（VQ-VAE 2）特征的单类分类器，以克服二类分类器的局限性。首先，我们通过在多个多光谱数据集上训练和测试EfficientNet-B4架构，强调了二分类器面临的泛化问题。接着，我们表明，由于基于VQ-VAE 2的分类器仅使用原始图像进行训练，它能够检测来自不同域且由训练中未使用过的架构生成的图像。最后，我们在相同的生成数据集上对两种分类器进行直接对比，凸显了基于VQ-VAE 2的检测器在泛化能力上的优越性。