<br>MFAE：用于域泛化人脸反欺骗的屏蔽频率自动编码器,IEEE Transactions on Information Forensics and Security

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.)

MFAE：用于域泛化人脸反欺骗的屏蔽频率自动编码器
IEEE Transactions on Information Forensics and Security ( IF 6.3 ) Pub Date : 2024-02-28 , DOI: 10.1109/tifs.2024.3371266
Tianyi Zheng ₁ , Bo Li ₂ , Shuang Wu ₂ , Ben Wan ₁ , Guodong Mu ₂ , Shice Liu ₂ , Shouhong Ding ₂ , Jia Wang ₁

Affiliation

泛化人脸反欺骗（FAS）最近引起了广泛关注。尽管许多现有方法在域内设置下表现良好，但模型在看不见的域中的性能并不令人满意。在本文中，我们将注意力转移到频域来寻求解决方案。具体来说，我们检查了 FAS 图像的不同频带分量的特征，并观察到该模型的跨域性能对低频特征非常敏感。为了减轻这种敏感性并提高模型在 FAS 跨域任务中的性能，我们提出了一种称为掩蔽频率自动编码器（MFAE）的新方法。 MFAE 随机屏蔽图像低频频谱上的一部分频率，然后根据所得嵌入重建图像。这种创新的掩模图像建模 (MIM) 策略可用作预训练视觉变换器 (ViT) 的自监督任务，这可以降低 ViT 编码器对域移位的敏感度。此外，我们在 MFAE 中添加了一个辅助内容正则化解码器，以鼓励编码器对低频特征不敏感。结果表明，该模型对低频特征不敏感，在广泛的公共数据集上表现良好，并且在跨域 FAS 任务中优于其他最先进的方法。

"点击查看英文标题和摘要"

MFAE: Masked Frequency Autoencoders for Domain Generalization Face Anti-Spoofing

The generalizable face anti-spoofing (FAS) has attracted much attention recently. Even though many existing methods perform well under intra-domain settings, the model’s performance in the unseen domain is not satisfying. In this paper, we shift our attention to the frequency domain to seek a solution. Specifically, we examine the characteristics of different frequency band components of FAS images and observe that the model’s cross-domain performance is very sensitive to low-frequency features. To alleviate this sensitivity and improve the model’s performance in FAS cross-domain tasks, we propose a new approach called Masked Frequency Autoencoders (MFAE). MFAE randomly masks a portion of frequencies on the low-frequency spectrum of the image and then reconstructs the image from the resulting embedding. This innovative Masked Image Modeling (MIM) strategy can be used as a self-supervised task for pre-training vision transformers (ViTs), which can reduce the ViT encoder’s sensitivity to domain shifts. Additionally, we add an auxiliary content-regularization decoder in our MFAE to encourage the encoder to be insensitive to low-frequency features. The results show that the model insensitive to low-frequency features performs well on extensive public datasets and outperforms other state-of-the-art methods in cross-domain FAS tasks.

更新日期：2024-02-28

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南