针对老年人设计自适应多模态认证模型，准确率达99.73%
AuthFormer: Adaptive Multimodal biometric authentication transformer for middle-aged and elderly people
- 基于交叉注意力与门控残差网络，动态融合多模态生物特征
- 在老年群体数据集上达到99.73%的认证准确率
- 仅需两层编码器，比传统Transformer更轻量
多模态生物识别方法克服了单一模态在安全性、鲁棒性和用户适应性上的局限。然而，现有方法大多依赖固定组合和数量的生物特征模态，限制了实际应用中的灵活性与适应性。为此，我们提出专为老年人设计的自适应多模态生物识别模型 AuthFormer，其在包含老年人生物特征数据的 LUTBIO 多模态生物识别数据库上进行训练。通过引入交叉注意力机制和门控残差网络（GRN），模型增强了对老年人生理变化的适应能力。实验表明，AuthFormer 达到 99.73% 的认证准确率。此外，其编码器仅需两层即可达到最优性能，相比传统 Transformer 模型显著降低复杂度。
原文摘要 · Abstract (English)
Multimodal biometric authentication methods address the limitations of unimodal biometric technologies in security, robustness, and user adaptability. However, most existing methods depend on fixed combinations and numbers of biometric modalities, which restricts flexibility and adaptability in real-world applications. To overcome these challenges, we propose an adaptive multimodal biometric authentication model, AuthFormer, tailored for elderly users. AuthFormer is trained on the LUTBIO multimodal biometric database, containing biometric data from elderly individuals. By incorporating a cross-attention mechanism and a Gated Residual Network (GRN), the model improves adaptability to physiological variations in elderly users. Experiments show that AuthFormer achieves an accuracy of 99.73%. Additionally, its encoder requires only two layers to perform optimally, reducing complexity compared to traditional Transformer-based models.
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。