Abstract
3D mask presentation attack detection is crucial for protecting face recognition systems against the rising threat of 3D mask attacks. While most existing methods utilize multimodal features or remote photoplethysmography (rPPG) signals to distinguish between real faces and 3D masks, they face significant challenges, such as the high costs associated with multimodal sensors and limited generalization ability. Detection-related text descriptions offer concise, universal information and are cost-effective to obtain. However, the potential of vision-language multimodal features for 3D mask presentation attack detection remains unexplored. In this paper, we propose a novel knowledge-based prompt learning framework to explore the strong generalization capability of vision-language models for 3D mask presentation attack detection. Specifically, our approach incorporates entities and triples from knowledge graphs into the prompt learning process, generating fine-grained, task-specific explicit prompts that effectively harness the knowledge embedded in pre-trained vision-language models. Furthermore, considering different input images may emphasize distinct knowledge graph elements, we introduce a visual-specific knowledge filter based on an attention mechanism to refine relevant elements according to the visual context. Additionally, we leverage causal graph theory insights into the prompt learning process to further enhance the generalization ability of our method. During training, a spurious correlation elimination paradigm is employed, which removes category-irrelevant local image patches using guidance from knowledge-based text features, fostering the learning of generalized causal prompts that align with category-relevant local patches. Experimental results demonstrate that the proposed method achieves state-of-the-art intra- and cross-scenario detection performance on benchmark datasets.
Abstract (translated)
3D面具呈现攻击检测对于保护面部识别系统免受日益增长的3D面具攻击威胁至关重要。尽管大多数现有的方法利用多模态特征或远程光体积描记图（rPPG）信号来区分真实人脸和3D面具，但它们面临着高昂的成本问题以及有限的泛化能力等重大挑战。与检测相关的文本描述提供了简洁、通用的信息，并且易于获取。然而，视觉-语言多模态特性在3D面具呈现攻击检测中的潜力尚未被探索。 本文提出了一种基于知识提示学习的新框架，以挖掘预训练视觉-语言模型的强大泛化能力来进行3D面具呈现攻击的检测。具体而言，我们的方法将知识图谱中的实体和三元组纳入到提示学习过程中，生成细粒度、任务特定的显式提示，从而有效地利用了嵌入在预先训练好的视觉-语言模型中的知识。 此外，考虑到不同输入图像可能强调不同的知识图谱元素，我们引入了一个基于注意力机制的视觉特异性知识过滤器来根据视觉上下文细化相关元素。另外，我们还借鉴因果图理论的思想进一步提升了方法的泛化能力，在训练过程中采用了虚假关联消除范式，该范式通过知识驱动的文本特征指导移除类别不相关的局部图像补丁，促进学习到与类别相关局部补丁相一致的一般性原因提示。 实验结果表明，所提出的方法在基准数据集上的内场景和跨场景检测性能上达到了最先进的水平。
URL
https://arxiv.org/abs/2505.03610
