DeepFidelity：面向 Deepfake 检测的感知伪造保真度评估
DeepFidelity: Perceptual Forgery Fidelity Assessment for Deepfake Detection
AI总结：
针对不同质量真实与伪造人脸难以区分的问题，本文提出 DeepFidelity 框架，通过感知伪造保真度评分和 SSAAFormer 增强特征建模，在多个基准上优于现有方法。
摘要：
Deepfake 检测是指检测图像或视频中人工生成或编辑的人脸，在视觉信息安全中发挥着重要作用。尽管近年来取得了可喜进展，但由于人脸伪造技术的复杂性和多变性，Deepfake 检测仍是一个具有挑战性的问题。现有 Deepfake 检测方法通常致力于通过设计复杂网络来提取特征，却忽视了人脸感知质量的影响。考虑到真实和伪造人脸质量分布的复杂性，本文提出一种名为 DeepFidelity 的新型 Deepfake 检测框架，通过挖掘人脸图像的感知伪造保真度，自适应地区分具有不同图像质量的真实和伪造人脸。具体而言，我们将不同质量的真实和伪造人脸数据映射到不同分数，以更细致的方式对其加以区分，从而提升模型识别复杂样本的能力。此外，我们提出一种名为 Symmetric Spatial Attention Augmentation based vision Transformer（SSAAFormer，基于对称空间注意力增强的视觉 Transformer）的网络结构，该结构利用人脸图像的对称性，促进网络在浅层建模地理长距离关系并增强局部特征。在多个基准数据集上进行的大量实验证明，所提方法优于最先进方法。
英文摘要：
Deepfake detection refers to detecting artificially generated or edited faces in images or videos, which plays an essential role in visual information security. Despite promising progress in recent years, Deepfake detection remains a challenging problem due to the complexity and variability of face forgery techniques. Existing Deepfake detection methods are often devoted to extracting features by designing sophisticated networks but ignore the influence of perceptual quality of faces. Considering the complexity of the quality distribution of both real and fake faces, we propose a novel Deepfake detection framework named DeepFidelity to adaptively distinguish real and fake faces with varying image quality by mining the perceptual forgery fidelity of face images. Specifically, we improve the model's ability to identify complex samples by mapping real and fake face data of different qualities to different scores to distinguish them in a more detailed way. In addition, we propose a network structure called Symmetric Spatial Attention Augmentation based vision Transformer (SSAAFormer), which uses the symmetry of face images to promote the network to model the geographic long-distance relationship at the shallow level and augment local features. Extensive experiments on multiple benchmark datasets demonstrate the superiority of the proposed method over state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
