Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing

2026-08-18

AI Summary

本文提出一种基于视觉特征空间的组合法医视觉提示学习框架，以解决开放世界面部反欺骗中的未知攻击问题。

Abstract

Open-world face anti-spoofing must address both covariate and semantic shifts: source and target domains differ in imaging conditions, while target domains contain diverse attack types absent from training. Existing prompt-based approaches often express spoofing through category semantics or language guidance, which is effective for modeling high-level concepts but is less suited to explicitly capturing the evolving fine-grained and spatially heterogeneous forensic evidence of unseen attacks. Motivated by the hypothesis that many unseen attacks can be characterized by new combinations of recurring visual cues, we propose a compositional forensic visual prompt learning framework that operates entirely in the visual feature space.Built on a frozen ViT-based vision foundation model, the framework employs patch-aware attention to refine a shared set of learnable micro-forensic primitives into localized forensic evidence units derived from image patches. Class-specific global contextual prompts then provide input-dependent routing weights that adaptively select and compose these primitives into compositional forensic visual prompts for real/spoof discrimination. The primitives are not assigned predefined semantic meanings; instead, their specialization and reuse emerge from shared parameterization and joint optimization across categories.Extensive experiments on nine open-world protocols demonstrate state-of-the-art performance, strong cross-domain generalization, and robust adaptation to unseen attacks.

Problem

• face anti-spoofing
• covariate shift
• semantic shift
• unseen attacks

Innovation

• Compositional Forensic Visual Prompting
• Patch-aware Attention
• Micro-forensic Primitives
• Adaptive Composition
• Cross-domain Generalization