CA-MoEiT: Generalizable Face Anti-spoofing via Dual Cross-Attention and Semi-fixed Mixture-of-Expert
文献类型：期刊论文
| 作者 | Liu, Ajian |
| 刊名 | INTERNATIONAL JOURNAL OF COMPUTER VISION
 |
| 出版日期 | 2024-06-15 |
| 页码 | 14 |
| 关键词 | Face anti-spoofing Domain generalization Vision transformer Mixture-of-experts |
| ISSN号 | 0920-5691 |
| DOI | 10.1007/s11263-024-02135-2 |
| 通讯作者 | Liu, Ajian(ajianliu92@gmail.com) |
| 英文摘要 | 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. |
| WOS关键词 | DOMAIN ADAPTATION |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001246813100001 |
| 出版者 | SPRINGER |
| 源URL | [http://ir.ia.ac.cn/handle/173211/58716]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心 |
| 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 |
| 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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。