用大模型提升身份证活体攻击检测跨国家泛化能力
Can Foundation Models Generalise the Presentation Attack Detection Capabilities on ID Cards?
- 用大模型在多国身份证数据上训练，提升跨国家泛化能力
- 真实图像（bona fide）是实现泛化关键，零样本效果显著
- 适合做跨域身份认证系统研究者参考
当前身份证活体攻击检测（PAD）的主要挑战在于应对不同国家发行的身份证时缺乏泛化能力。由于隐私保护限制，多数PAD系统仅在1-3个身份证文档上训练，导致在新国家测试时性能下降，难以满足商业需求。本文探索基于大规模预训练基础模型（FM）提升该任务的泛化能力。实验采用零样本与微调两种策略，使用两个数据集：一个基于智利身份证的私有数据集，另一个包含芬兰、西班牙和斯洛伐克三国身份证的开放集数据集。结果表明，真实图像（bona fide images）是实现良好泛化的决定性因素。
原文摘要 · Abstract (English)
Nowadays, one of the main challenges in presentation attack detection (PAD) on ID cards is obtaining generalisation capabilities for a diversity of countries that are issuing ID cards. Most PAD systems are trained on one, two, or three ID documents because of privacy protection concerns. As a result, they do not obtain competitive results for commercial purposes when tested in an unknown new ID card country. In this scenario, Foundation Models (FM) trained on huge datasets can help to improve generalisation capabilities. This work intends to improve and benchmark the capabilities of FM and how to use them to adapt the generalisation on PAD of ID Documents. Different test protocols were used, considering zero-shot and fine-tuning and two different ID card datasets. One private dataset based on Chilean IDs and one open-set based on three ID countries: Finland, Spain, and Slovakia. Our findings indicate that bona fide images are the key to generalisation.
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。