用基础模型提升人脸活体检测泛化能力，少样本也能高效部署。
FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection
- 基于基础模型，通过LoRA微调与分类头联合训练。
- 在多种数据条件下表现优异，合成数据训练也有效。
- 适合少样本场景，推动可复现的活体检测研究。
尽管人脸识别系统近年来性能大幅提升，仍面临投影攻击等威胁，亟需具备强泛化能力的通用活体检测（PAD）算法。现有方法存在未知场景泛化差、训练数据需求量大两大问题。基础模型（FM）在大规模数据上预训练，能良好迁移到未见领域，并在少量数据下实现高效任务适配。本文首次将基础模型应用于PAD任务，提出基于LoRA权重微调并联合训练分类头的架构FoundPAD。该模型在不同数据条件下表现出色，即使使用合成数据训练亦能取得竞争力结果。为促进可复现性与进一步研究，我们公开了FoundPAD代码库：https://github.com/gurayozgur/FoundPAD。
原文摘要 · Abstract (English)
Although face recognition systems have seen a massive performance enhancement in recent years, they are still targeted by threats such as presentation attacks, leading to the need for generalizable presentation attack detection (PAD) algorithms. Current PAD solutions suffer from two main problems: low generalization to unknown cenarios and large training data requirements. Foundation models (FM) are pre-trained on extensive datasets, achieving remarkable results when generalizing to unseen domains and allowing for efficient task-specific adaption even when little training data are available. In this work, we recognize the potential of FMs to address common PAD problems and tackle the PAD task with an adapted FM for the first time. The FM under consideration is adapted with LoRA weights while simultaneously training a classification header. The resultant architecture, FoundPAD, is highly generalizable to unseen domains, achieving competitive results in several settings under different data availability scenarios and even when using synthetic training data. To encourage reproducibility and facilitate further research in PAD, we publicly release the implementation of FoundPAD at https://github.com/gurayozgur/FoundPAD .
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。