融合视觉与文本信息，提升身份证伪造检测在跨域场景下的鲁棒性
From Vision to Text: A Compact Multimodal Approach for Robust, Cross-Domain Presentation Attack Detection on ID Cards
- 设计紧凑的多模态模型，结合图像与文本特征进行检测
- 在零样本设置下表现不佳，凸显真实数据重要性
- 呼吁构建更真实多样数据集，重新评估合成数据基准
跨域差异严重挑战身份证伪造攻击检测（PAD）性能，受限于隐私问题可用数据稀缺。本文提出一种基于新型生成与判别模块的紧凑多模态模型，融合视觉与文本信息以检测真实与合成身份证图像。尽管监督微调后多模态模型具备强泛化能力，但在零样本设置下表现失败。研究结果强调模型容量与真实世界数据对可靠PAD至关重要，现有合成数据集可能无法反映实际挑战。本文主张重新评估合成数据作为基准的适用性，并强调需构建更真实、多样化的数据集以推动PAD研究进展。
原文摘要 · Abstract (English)
Cross-domain shifts challenge Presentation Attack Detection (PAD) on ID Cards, given the restricted data available due to privacy concerns. This work proposes a compact multimodal model, based on new generative and discriminative blocks, which combines visual and textual data for PAD on genuine and synthetic ID images. While multimodal models exhibit strong generalisation after supervised fine-tuning, they fail in zero-shot settings. Our findings underscore that model capacity and real-world data are essential for reliable PAD, while existing synthetic datasets may not reflect real-world challenges. We argue for a re-evaluation of synthetic data as a benchmark and emphasise the need for more realistic, diverse datasets to advance PAD research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。