CA-MoEiT: Generalizable Face Anti-spoofing via Dual Cross-Attention and Semi-fixed Mixture-of-Expert

doi:10.1007/s11263-024-02135-2

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	CA-MoEiT: Generalizable Face Anti-spoofing via Dual Cross-Attention and Semi-fixed Mixture-of-Expert
	Liu, Ajian
发表期刊	INTERNATIONAL JOURNAL OF COMPUTER VISION
ISSN	0920-5691
	2024-06-15
页码	14
通讯作者	Liu, Ajian(ajianliu92@gmail.com)
摘要	Although the generalization of face anti-spo-ofing (FAS) is increasingly concerned, it is still in the initial stage to solve it based on Vision Transformer (ViT). In this paper, we present a cross-domain FAS framework, dubbed the Transformer with dual Cross-Attention and semi-fixed Mixture-of-Expert (CA-MoEiT), for stimulating the generalization of Face Anti-Spoofing (FAS) from three aspects: (1) Feature augmentation. We insert a MixStyle after PatchEmbed layer to synthesize diverse patch embeddings from novel domains and enhance the generalizability of the trained model. (2) Feature alignment. We design a dual cross-attention mechanism which extends the self-attention to align the common representation from multiple domains. (3) Feature complement. We design a semi-fixed MoE (SFMoE) to selectively replace MLP by introducing a fixed super expert. Benefiting from the gate mechanism in SFMoE, professional experts are adaptively activated with independent learning domain-specific information, which is used as a supplement to domain-invariant features learned by the super expert to further improve the generalization. It is important that the above three technologies can be compatible with any variant of ViT as plug-and-play modules. Extensive experiments show that the proposed CA-MoEiT is effective and outperforms the state-of-the-art methods on several public datasets.
关键词	Face anti-spoofing Domain generalization Vision transformer Mixture-of-experts
DOI	10.1007/s11263-024-02135-2
关键词[WOS]	DOMAIN ADAPTATION
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001246813100001
出版者	SPRINGER
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58717
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
通讯作者	Liu, Ajian
作者单位	Chinese Acad Sci CASIA, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Liu, Ajian. CA-MoEiT: Generalizable Face Anti-spoofing via Dual Cross-Attention and Semi-fixed Mixture-of-Expert[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2024:14.
APA	Liu, Ajian.(2024).CA-MoEiT: Generalizable Face Anti-spoofing via Dual Cross-Attention and Semi-fixed Mixture-of-Expert.INTERNATIONAL JOURNAL OF COMPUTER VISION,14.
MLA	Liu, Ajian."CA-MoEiT: Generalizable Face Anti-spoofing via Dual Cross-Attention and Semi-fixed Mixture-of-Expert".INTERNATIONAL JOURNAL OF COMPUTER VISION (2024):14.