提出GRU-AUNet，提升无接触指纹防伪的跨域泛化能力。
GRU-AUNet: A Domain Adaptation Framework for Contactless Fingerprint Presentation Attack Detection
- 融合Swin Transformer与GRU注意力，增强特征提取。
- 在三个数据集上平均误报率0.09%，拒真率1.2%。
- 适合需要高鲁棒性的无接触生物识别系统部署。
无接触指纹虽提升用户体验，但更易遭受伪造攻击。当前反伪造方法依赖领域自适应学习，限制了泛化与可扩展性。为此，本文提出GRU-AUNet，一种结合Swin Transformer-based UNet架构、GRU增强注意力机制、瓶颈层动态滤波网络及联合焦点损失与对比损失函数的领域自适应方法。在真实与伪造指纹图像上训练后，该模型在CLARKSON、COLFISPOOF和IIITD数据集上均表现出强抗伪造能力，平均BPCER为0.09%，APCER为1.2%，优于现有先进领域自适应方法。
原文摘要 · Abstract (English)
Although contactless fingerprints offer user comfort, they are more vulnerable to spoofing. The current solution for anti-spoofing in the area of contactless fingerprints relies on domain adaptation learning, limiting their generalization and scalability. To address these limitations, we introduce GRU-AUNet, a domain adaptation approach that integrates a Swin Transformer-based UNet architecture with GRU-enhanced attention mechanisms, a Dynamic Filter Network in the bottleneck, and a combined Focal and Contrastive Loss function. Trained in both genuine and spoof fingerprint images, GRU-AUNet demonstrates robust resilience against presentation attacks, achieving an average BPCER of 0.09\% and APCER of 1.2\% in the CLARKSON, COLFISPOOF, and IIITD datasets, outperforming state-of-the-art domain adaptation methods.
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。