arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.04953eess.IVeess.SP
收藏

基于自适应平均池化注意力Vision Transformer的人脸反欺骗

Adaptive-avg-pooling based Attention Vision Transformer for Face Anti-spoofing

Jichen Yang, Fangfan Chen, Rohan Kumar Das, Zhengyu Zhu, Shunsi Zhang

AI总结:

提出基于自适应平均池化注意力Vision Transformer(AAViT),用自适应平均池化和注意力模块替代传统平均值计算模块以减少信息丢失,在Replay-Attack数据库上取得更低等错误率,优于ResNet等网络。

摘要:

传统Vision Transformer由transformer编码器和多层感知机(MLP)两部分组成。前者负责特征学习以获得更好的表示,而后者负责分类。其中,MLP由两个全连接(FC)层、平均值计算、FC层和softmax层构成。然而,由于使用平均值计算模块,一些有用信息可能会丢失,我们计划通过使用替代框架来保留这些信息。在这项工作中,我们提出了一种名为基于自适应平均池化注意力Vision Transformer(AAViT)的新型Vision Transformer,它使用自适应平均池化和注意力模块来替代平均值计算模块。我们使用Replay-Attack数据库探索了所提出的AAViT在人脸反欺骗方面的研究。实验表明,AAViT通过产生更低的等错误率在人脸反欺骗中优于Vision Transformer。此外,我们发现所提出的AAViT在Replay-Attack语料库上的表现远优于一些常用的神经网络(如ResNet)和其他一些已知系统。

英文摘要:

Traditional vision transformer consists of two parts: transformer encoder and multi-layer perception (MLP). The former plays the role of feature learning to obtain better representation, while the latter plays the role of classification. Here, the MLP is constituted of two fully connected (FC) layers, average value computing, FC layer and softmax layer. However, due to the use of average value computing module, some useful information may get lost, which we plan to preserve by the use of alternative framework. In this work, we propose a novel vision transformer referred to as adaptive-avg-pooling based attention vision transformer (AAViT) that uses modules of adaptive average pooling and attention to replace the module of average value computing. We explore the proposed AAViT for the studies on face anti-spoofing using Replay-Attack database. The experiments show that the AAViT outperforms vision transformer in face anti-spoofing by producing a reduced equal error rate. In addition, we found that the proposed AAViT can perform much better than some commonly used neural networks such as ResNet and some other known systems on the Replay-Attack corpus.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑