当前位置: X-MOL 学术IEEE Trans. Inform. Forensics Secur. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
IFAST: Weakly Supervised Interpretable Face Anti-Spoofing From Single-Shot Binocular NIR Images
IEEE Transactions on Information Forensics and Security ( IF 6.3 ) Pub Date : 2024-09-23 , DOI: 10.1109/tifs.2024.3465930
Jiancheng Huang, Donghao Zhou, Jianzhuang Liu, Linxiao Shi, Shifeng Chen

Single-shot face anti-spoofing (FAS) is a key technique for securing face recognition systems, relying solely on static images as input. However, single-shot FAS remains a challenging and under-explored problem due to two reasons: 1) On the data side, learning FAS from RGB images is largely context-dependent, and single-shot images without additional annotations contain limited semantic information. 2) On the model side, existing single-shot FAS models struggle to provide proper evidence for their decisions, and FAS methods based on depth estimation require expensive per-pixel annotations. To address these issues, we construct and release a large binocular NIR image dataset named BNI-FAS, which contains more than 300,000 real face and plane attack images, and propose an Interpretable FAS Transformer (IFAST) that requires only weak supervision to produce interpretable predictions. Our IFAST generates pixel-wise disparity maps using the proposed disparity estimation Transformer with Dynamic Matching Attention (DMA) blocks. Besides, we design a confidence map generator to work in tandem with a dual-teacher distillation module to obtain the final discriminant results. Comprehensive experiments show that our IFAST achieves state-of-the-art performance on BNI-FAS, verifying its effectiveness of single-shot FAS on binocular NIR images. The project page is available at https://ifast-bni.github.io/ .

中文翻译:


IFAST:来自单发双目 NIR 图像的弱监督可解释人脸反欺骗



单发人脸反欺骗 (FAS) 是保护人脸识别系统的关键技术,仅依赖静态图像作为输入。然而,由于两个原因,单发 FAS 仍然是一个具有挑战性且未被充分探索的问题:1) 在数据方面,从 RGB 图像中学习 FAS 在很大程度上取决于上下文,没有额外注释的单发图像包含有限的语义信息。2) 在模型方面,现有的单发 FAS 模型难以为其决策提供适当的证据,而基于深度估计的 FAS 方法需要昂贵的每像素注释。为了解决这些问题,我们构建并发布了一个名为 BNI-FAS 的大型双目 NIR 图像数据集,其中包含超过 300,000 张真实的人脸和平面攻击图像,并提出了一种可解释的 FAS 转换器 (IFAST),它只需要弱监督即可产生可解释的预测。我们的 IFAST 使用提出的视差估计 Transformer with Dynamic Matching Attention (DMA) 块生成像素视差图。此外,我们设计了一个置信度图生成器,与双教师蒸馏模块协同工作,以获得最终的判别结果。综合实验表明,我们的 IFAST 在 BNI-FAS 上实现了最先进的性能,验证了其在双目 NIR 图像上的单次 FAS 的有效性。项目页面位于 https://ifast-bni.github.io/ 。
更新日期:2024-09-23
down
wechat
bug