arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.01030cs.CV
收藏

学习发现伪造线索用于人脸伪造检测

Learning to Discover Forgery Cues for Face Forgery Detection

Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；RealAI Inc（RealAI公司）

Jiahe Tian, Peng Chen, Cai Yu, Xiaomeng Fu, Xi Wang, Jiao Dai, Jizhong Han

备注：
TIFS 2024
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出弱监督模型 FoCus，通过分类注意力区域提议和互补学习在不成对人脸中定位伪造线索，生成更优篡改图以提升检测器的可解释性与性能。

摘要：

定位篡改图，即对伪造线索进行像素级标注，对于在人脸伪造检测中提供可解释的检测结果至关重要。相关的学习目标也已被广泛用作辅助任务，以提升检测器的分类性能，但这些方法需要成对的真实人脸与伪造人脸之间的比较，才能获得篡改图作为监督。这一要求限制了它们在不成对人脸上的适用性，并与现实场景相矛盾。此外，所使用的比较方法会标注所有发生变化的像素，包括由压缩和上采样引入的噪声。使用这样的图作为监督会阻碍对可利用线索的学习，并使模型容易过拟合。为了解决这些问题，本文提出了一种弱监督模型，名为 Forgery Cue Discovery（FoCus），用于在不成对人脸中定位伪造线索。与一些声称在注意力图中定位伪造区域的检测器不同，FoCus 的设计旨在规避它们只能捕获部分且不准确的伪造线索的缺点。具体而言，我们提出了一个分类注意力区域提议模块，用于在分类过程中定位伪造线索，以及一个互补学习模块，以促进对更丰富线索的学习。所生成的篡改图可以作为更好的监督来增强人脸伪造检测器。与现有方法相比，所提出的 FoCus 的篡改图可视化展现出更优的可解释性和鲁棒性。在五个数据集和四个多任务模型上的实验证明了 FoCus 在数据集内和跨数据集评估中的有效性。

英文摘要：

Locating manipulation maps, i.e., pixel-level annotation of forgery cues, is crucial for providing interpretable detection results in face forgery detection. Related learning objects have also been widely adopted as auxiliary tasks to improve the classification performance of detectors whereas they require comparisons between paired real and forged faces to obtain manipulation maps as supervision. This requirement restricts their applicability to unpaired faces and contradicts real-world scenarios. Moreover, the used comparison methods annotate all changed pixels, including noise introduced by compression and upsampling. Using such maps as supervision hinders the learning of exploitable cues and makes models prone to overfitting. To address these issues, we introduce a weakly supervised model in this paper, named Forgery Cue Discovery (FoCus), to locate forgery cues in unpaired faces. Unlike some detectors that claim to locate forged regions in attention maps, FoCus is designed to sidestep their shortcomings of capturing partial and inaccurate forgery cues. Specifically, we propose a classification attentive regions proposal module to locate forgery cues during classification and a complementary learning module to facilitate the learning of richer cues. The produced manipulation maps can serve as better supervision to enhance face forgery detectors. Visualization of the manipulation maps of the proposed FoCus exhibits superior interpretability and robustness compared to existing methods. Experiments on five datasets and four multi-task models demonstrate the effectiveness of FoCus in both in-dataset and cross-dataset evaluations.

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。

↑