Year: 2021
Type: preprint
Abstract: With various facial manipulation techniques arising, face forgery detection has drawn growing attention due to security concerns. Previous works always formulate face forgery detection as a classification problem based on cross-entropy loss, which emphasizes category-level differences rather than the essential discrepancies between real and fake faces, limiting model generalization in unseen domains. To address this issue, we propose a novel face forgery detection framework, named Dual Contrastive Learning (DCL), which specially constructs positive and negative paired data and performs designed contrastive learning at different granularities to learn generalized feature representation. Concretely, combined with the hard sample selection strategy, Inter-Instance Contrastive Learning (Inter-ICL) is first proposed to promote task-related discriminative features learning by especially constructing instance pairs. Moreover, to further explore the essential discrepancies, Intra-Instance Contrastive Learning (Intra-ICL) is introduced to focus on the local content inconsistencies prevalent in the forged faces by constructing local-region pairs inside instances. Extensive experiments and visualizations on several datasets demonstrate the generalization of our method against the state-of-the-art competitors.
Source: arXiv (Cornell University)
Authors: Sun, Ke, Yao, Taiping, Chen, Shen, Ding, Shouhong, L, Jilin, Ji, Rongrong
Institutions: Xiamen University, Tencent (China)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: 基于弱监督学习的机载地/海小目标检测研究, G1300220747, G1353530241, G1627692989, 面向深度学习的对抗攻防技术研究, G187639494, G2264607873, G2564228358, 恶劣环境下遥感图像小目标鲁棒检测算法研究, G2785666877, G390962370, G5334537529, G5670123517, G6075090814, G6417266703, G7630636626, G7701267250, 面向图敏感深度学习的结构化超图研究, G8507526577, G95228445, G955830527
OpenAlex ID: W4226166157