With the rapid development of the deep generative models (such as Generative Adversarial Networks and Auto-encoders), AI-synthesized images of human face are now of such high qualities that humans can hardly distinguish them from pristine ones. Although existing detection methods have shown high performance in specific evaluation settings, e.g., on images from seen models or on images without real-world post-processings, they tend to suffer serious performance degradation in real-world scenarios where testing images can be generated by more powerful generation models or combined with various post-processing operations. To address this issue, we propose a Global and Local Feature Fusion (GLFF) to learn rich and discriminative representations by combining multi-scale global features from the whole image with refined local features from informative patches for face forgery detection. GLFF fuses information from two branches: global branch to extract multi-scale semantic features and local branch to select informative patches for detailed local artifacts extraction. Due to the lack of face forgery dataset simulating real-world applications for evaluation, we further create a challenging face forgery dataset, named DeepFakeFaceForensics (DF$^3$), which contains 6 state-of-the-art generation models and a variety of post-processing techniques to approach the real-world scenarios. Experimental results demonstrate the superiority of our method to the state-of-the-art methods on the proposed DF^3 dataset and three other open-source datasets.
翻译:随着深层基因化模型(如General Adversarial Networks和Auto-colders)的迅速发展,AI合成的人类面貌图像现在具有如此高的品质,人类很难将其与原始的图像区分开来。虽然现有的检测方法在具体评估环境中表现出很高的性能,例如,在从所见模型或图像上显示高超的性能,而没有现实世界的后处理器,它们往往在现实世界的情景中遭受严重性能退化,在现实世界中,通过更强大的生成模型或与各种后处理操作相结合,来测试图像。为了解决这个问题,我们提议建立全球和本地的特异性组合(GLFF),通过将整个图像中的多尺度全球特征与用于表面伪造检测的信息补全的局部特征结合起来,来学习丰富而具有歧视性的表现形式。 GLFF将来自两个分支的信息结合起来:全球分支提取多尺度的语系特征特征,以及地方分支为详细本地艺术品提取的图案。由于缺乏面伪造数据集模拟真实世界的应用,我们进一步创建了一个具有挑战性面值的面值的数据集,而后期中含有实际数据-FA-FAS-FS-servic-de-de-deal-de-de-de-de-de-de-deal-de-de-pal-pal-pal-de-de-de-pal-pal-de-pal-pal-de-s-s-de-de-de-de-pal-pal-pal-pal-dal-dal-dal-pal-dal-d-dal-dal-d-d-d-d-d-d-s-s-s-s-s-d-s-s-d-d-d-d-d-d-d-d-s-s-d-d-d-s-s-d-d-pal-d-d-s-d-d-d-d-d-s-s-d-s-s-d-d-s-s-d-s-d-d-s-s-s-d-d-d-d-dal-d-d-d-d-d-d-d-d-