用多视角文本增强面部反伪造模型的泛化能力
Multi-View Slot Attention Using Paraphrased Texts for Face Anti-Spoofing
- 引入多视角槽注意力机制，从视觉片段中挖掘局部与全局特征
- 通过多文本对齐提升语义鲁棒性，在跨域测试中优于现有方法
- 适合需要高泛化性能的安防场景或实际部署中的反伪造系统
近期基于CLIP的面部反伪造（FAS）方法在跨域场景下表现优异，但未能充分挖掘CLIP的图像块嵌入标记，难以捕捉关键伪造线索。同时，这些方法每类仅使用单一文本提示（如'真实'或'伪造'），限制了泛化能力。为此，本文提出MVP-FAS框架，包含两个核心模块：多视角槽注意力（MVS）和多文本块对齐（MTPA）。MVS通过多种改写文本从不同视角提取局部细节与全局上下文特征；MTPA将图像块与多种文本表示对齐，增强语义鲁棒性。大量实验表明，MVP-FAS在跨域数据集上显著优于现有最先进方法。代码已开源：https://github.com/Elune001/MVP-FAS。
原文摘要 · Abstract (English)
Recent face anti-spoofing (FAS) methods have shown remarkable cross-domain performance by employing vision-language models like CLIP. However, existing CLIP-based FAS models do not fully exploit CLIP's patch embedding tokens, failing to detect critical spoofing clues. Moreover, these models rely on a single text prompt per class (e.g., 'live' or 'fake'), which limits generalization. To address these issues, we propose MVP-FAS, a novel framework incorporating two key modules: Multi-View Slot attention (MVS) and Multi-Text Patch Alignment (MTPA). Both modules utilize multiple paraphrased texts to generate generalized features and reduce dependence on domain-specific text. MVS extracts local detailed spatial features and global context from patch embeddings by leveraging diverse texts with multiple perspectives. MTPA aligns patches with multiple text representations to improve semantic robustness. Extensive experiments demonstrate that MVP-FAS achieves superior generalization performance, outperforming previous state-of-the-art methods on cross-domain datasets. Code: https://github.com/Elune001/MVP-FAS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。