Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912312769642496 |
|---|---|
| author | Guo, Jiabao Liu, Ajian Diao, Yunfeng Zhang, Jin Ma, Hui Zhao, Bo Hong, Richang Wang, Meng |
| author_facet | Guo, Jiabao Liu, Ajian Diao, Yunfeng Zhang, Jin Ma, Hui Zhao, Bo Hong, Richang Wang, Meng |
| contents | The challenge of Domain Generalization (DG) in Face Anti-Spoofing (FAS) is the significant interference of domain-specific signals on subtle spoofing clues. Recently, some CLIP-based algorithms have been developed to alleviate this interference by adjusting the weights of visual classifiers. However, our analysis of this class-wise prompt engineering suffers from two shortcomings for DG FAS: (1) The categories of facial categories, such as real or spoof, have no semantics for the CLIP model, making it difficult to learn accurate category descriptions. (2) A single form of prompt cannot portray the various types of spoofing. In this work, instead of class-wise prompts, we propose a novel Content-aware Composite Prompt Engineering (CCPE) that generates instance-wise composite prompts, including both fixed template and learnable prompts. Specifically, our CCPE constructs content-aware prompts from two branches: (1) Inherent content prompt explicitly benefits from abundant transferred knowledge from the instruction-based Large Language Model (LLM). (2) Learnable content prompts implicitly extract the most informative visual content via Q-Former. Moreover, we design a Cross-Modal Guidance Module (CGM) that dynamically adjusts unimodal features for fusion to achieve better generalized FAS. Finally, our CCPE has been validated for its effectiveness in multiple cross-domain experiments and achieves state-of-the-art (SOTA) results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04470 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering Guo, Jiabao Liu, Ajian Diao, Yunfeng Zhang, Jin Ma, Hui Zhao, Bo Hong, Richang Wang, Meng Computer Vision and Pattern Recognition The challenge of Domain Generalization (DG) in Face Anti-Spoofing (FAS) is the significant interference of domain-specific signals on subtle spoofing clues. Recently, some CLIP-based algorithms have been developed to alleviate this interference by adjusting the weights of visual classifiers. However, our analysis of this class-wise prompt engineering suffers from two shortcomings for DG FAS: (1) The categories of facial categories, such as real or spoof, have no semantics for the CLIP model, making it difficult to learn accurate category descriptions. (2) A single form of prompt cannot portray the various types of spoofing. In this work, instead of class-wise prompts, we propose a novel Content-aware Composite Prompt Engineering (CCPE) that generates instance-wise composite prompts, including both fixed template and learnable prompts. Specifically, our CCPE constructs content-aware prompts from two branches: (1) Inherent content prompt explicitly benefits from abundant transferred knowledge from the instruction-based Large Language Model (LLM). (2) Learnable content prompts implicitly extract the most informative visual content via Q-Former. Moreover, we design a Cross-Modal Guidance Module (CGM) that dynamically adjusts unimodal features for fusion to achieve better generalized FAS. Finally, our CCPE has been validated for its effectiveness in multiple cross-domain experiments and achieves state-of-the-art (SOTA) results. |
| title | Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.04470 |