用语言模型提升人脸反欺骗的泛化能力，减少跨域训练冗余。
InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing
- 通过文本指令分解内容与风格，引导视觉语言模型理解攻击本质。
- 单域训练下实现多域泛化，在多个数据集上准确率领先现有方法。
- 适合需要低训练成本、强泛化能力的工业级活体检测场景。
人脸反欺骗（FAS）旨在构建能抵御多种攻击的鲁棒系统。当前研究主要聚焦跨域泛化，但仍面临两大挑战：对攻击类型语义理解有限，以及跨域训练存在冗余。本文通过引入视觉语言模型（VLMs）增强对输入图像的感知能力，解决第一项挑战；采用元域策略学习一个统一模型以提升多域泛化性能。提出的InstructFLIP是一种新型指令微调框架，仅需单一领域数据训练，即可通过文本引导实现跨域泛化。其核心思想是将指令显式解耦为内容与风格两部分：内容指令关注欺骗的本质语义，风格指令则捕捉环境与相机特性带来的变化。大量实验表明，InstructFLIP在多个数据集上优于现有最优模型，显著降低跨域训练冗余。项目主页见 https://kunkunlin1221.github.io/InstructFLIP。
原文摘要 · Abstract (English)
Face anti-spoofing (FAS) aims to construct a robust system that can withstand diverse attacks. While recent efforts have concentrated mainly on cross-domain generalization, two significant challenges persist: limited semantic understanding of attack types and training redundancy across domains. We address the first by integrating vision-language models (VLMs) to enhance the perception of visual input. For the second challenge, we employ a meta-domain strategy to learn a unified model that generalizes well across multiple domains. Our proposed InstructFLIP is a novel instruction-tuned framework that leverages VLMs to enhance generalization via textual guidance trained solely on a single domain. At its core, InstructFLIP explicitly decouples instructions into content and style components, where content-based instructions focus on the essential semantics of spoofing, and style-based instructions consider variations related to the environment and camera characteristics. Extensive experiments demonstrate the effectiveness of InstructFLIP by outperforming SOTA models in accuracy and substantially reducing training redundancy across diverse domains in FAS. Project website is available at https://kunkunlin1221.github.io/InstructFLIP.
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。