MF 2 ShrT: Multi-Modal Feature Fusion using Shared Layered Transformer for Face Anti-Spoofing

Author:

Antil Aashania1ORCID,Dhiman Chhavi1ORCID

Affiliation:

1. Department of Electronics and Communication Engineering, Delhi Technological University, New Delhi, Delhi, India

Abstract

In recent times, Face Anti-spoofing (FAS) has gained significant attention in both academic and industrial domains. Although various CNN-based solutions have emerged, multi-modal approaches incorporating RGB, depth, and IR have exhibited better performance than unimodal classifiers. The increasing veracity of modern presentation attack instruments results in a persistent need to enhance the performance of such models. Recently, self-attention-based vision transformers (ViT) have become a popular choice in this field. Their fundamental aspects for multimodal FAS have not been thoroughly explored yet. Therefore, we propose a novel framework for FAS called MF 2 ShrT, which is based on a pre-trained vision transformer. The proposed framework uses overlap patches and parameter sharing in the ViT network, allowing it to utilize multiple modalities in a computationally efficient manner. Furthermore, to effectively fuse intermediate features from different encoders of each ViT, we explore a T-encoder-based hybrid feature block enabling the system to identify correlations and dependencies across different modalities. MF 2 ShrT outperforms conventional vision transformers and achieves state-of-the-art performance on benchmarks CASIA-SURF and WMCA, demonstrating the efficiency of transformer-based models for PAD.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture

Reference61 articles.

1. Presentation Attack Detection Methods for Face Recognition Systems: A Comprehensive Survey;Ramachandra R.;ACM Computing Surveys (CSUR),2017

2. Z. Zhang, J. Yan, S. Liu, Z. Lei, D. Yi and S. Z. Li, "A face antispoofing database with diverse attacks," in 5th IAPR International Conference on Biometrics (ICB), New Delhi, India, 2012.

3. I. Chingovska, A. Anjos and S. Marcel, "On the effectiveness of local binary patterns in face anti-spoofing," in BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG), Darmstadt, Germany, 2012.

4. SPGAN: Face Forgery Using Spoofing Generative Adversarial Networks;Li Y.;ACM transactions on Multimedia Computing, Communications, and Applications,2021

5. Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection;Liu A.;IEEE Transactions on Information Forensics and Security,2021

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3