With the rapid development of facial forgery techniques, forgery detection has attracted more and more attention due to security concerns. Existing approaches attempt to use frequency information to mine subtle artifacts under high-quality forged faces. However, the exploitation of frequency information is coarse-grained, and more importantly, their vanilla learning process struggles to extract fine-grained forgery traces. To address this issue, we propose a progressive enhancement learning framework to exploit both the RGB and fine-grained frequency clues. Specifically, we perform a fine-grained decomposition of RGB images to completely decouple the real and fake traces in the frequency space. Subsequently, we propose a progressive enhancement learning framework based on a two-branch network, combined with self-enhancement and mutual-enhancement modules. The self-enhancement module captures the traces in different input spaces based on spatial noise enhancement and channel attention. The Mutual-enhancement module concurrently enhances RGB and frequency features by communicating in the shared spatial dimension. The progressive enhancement process facilitates the learning of discriminative features with fine-grained face forgery clues. Extensive experiments on several datasets show that our method outperforms the state-of-the-art face forgery detection methods.
翻译:随着面部伪造技术的迅速发展,伪造检测由于安全考虑而吸引了越来越多的关注。现有的方法试图利用频率信息在高质量伪造面容下开采微妙的文物。但是,对频率信息的利用是粗粗粗的,更重要的是,香草学习过程在提取细细的伪造痕迹方面挣扎不休。为了解决这一问题,我们提议了一个逐步加强学习的框架,以利用RGB和细微采集的频率线索。具体地说,我们对RGB图像进行细微的分解,以完全消除频率空间中真实的和假的痕迹。随后,我们提出一个渐进式增强学习框架,以两层网络为基础,同时结合自我增强和相互增强模块。自我增强模块在空间噪音增强和频道关注的基础上捕捉不同输入空间的痕迹。相互增强模块同时通过在共享空间层面进行交流来增强RGB和频率特征。逐步增强过程有助于学习带有精细的面部伪造图像的歧视性特征。我们用多种数据结构测试方法展示了我们的各种数据结构。