[论文] FaceJev: Direct Visual Decisions for Face Forgery Detection
论文概要
研究领域: CV
作者: Siran Peng, Tianshuo Zhang, Yibo Xue, Ajian Liu, Haoyuan Zhang, Weisong Zhao, Shuhuan Chen, Xiangyu Zhu, Zhen Lei
发布时间: 2026-11-16
arXiv: 2611.21604
中文摘要
人脸伪造检测方法在已见操作上表现良好,但对未见操作的泛化能力较差。多模态大语言模型(MLLM)能识别人脸部位并评估其视觉合理性,但现有基于 MLLM 的方法通常通过文本解释来表达这些判断,很少将个体部位决策作为显式学习目标。我们提出 FaceJev,一种通过直接视觉决策进行人脸伪造检测的 MLLM 方法。遵循 Jev 的表述,FaceJev 使用共享图像编码回答关于八个面部部位的独立问题,并从原生答案 logits 中读取异常概率。如果任何部位被预测为异常,则判定该人脸为伪造,将检测结果与部位决策直接关联。我们构建了约 16 万张带八个人脸部位二元异常目标的 PartForensics 数据集来监督这些决策。我们还提出 FS-GRPO,通过与替代方案进行精确奖励比较来优化每个部位决策,同时使用检测奖励和部位奖励。FaceJev 在未见操作上超越最强基线 7.25 个百分点。大量消融实验验证了设计选择和主要组件的有效性。
原文摘要
Face forgery detection methods often perform well on seen manipulations but generalize poorly to unseen ones. Multimodal Large Language Models (MLLMs) can recognize facial parts and assess their visual plausibility. Existing MLLM-based methods typically express these judgments through textual explanations, but seldom treat individual part decisions as explicit learning targets. We present FaceJev, an MLLM-based method for face forgery detection through direct visual decisions. Following the Jev formulation, FaceJev answers eight independent questions about facial parts using a shared image encoding and reads anomaly probabilities from the native answer logits. A face is classified as forged if any part is predicted to be abnormal, directly linking the detection result to the part decisions...
自动采集于 2026-11-18
#论文 #arXiv #CV #小凯