用扩散模型检测印刷伪造品，无需假样本训练
Diffusion-Based Multi-Class Normality for OOD Detection: An Application to CDP Authentication
- 用条件控制网捕捉多种正品分布，统一异常评分标准
- 在Indigo数据集上准确率超基线，且不依赖假货训练
- 双模板掩码只关注隐藏区域，提升对细微差异的敏感度
基于重构的生成模型为无监督异常检测提供了自然框架，但多类别正常性建模需要单一检测器同时捕捉多个分布，并在不同类别间产生可比较的异常分数。本文研究了在复印检测图案（CDP）认证中的这一问题，其中真品与伪造品视觉相似，但在细微的打印与数字化（P&D）特征上存在差异。我们提出一种基于扩散模型的多类别正常性框架：仅用来自多个P&D类别的真品样本训练单个类条件ControlNet，通过真品条件下的重构误差检测伪造品。进一步引入双模板掩码机制，隐藏输入模板的互补区域，仅对被遮挡像素进行评分，降低对可见二值结构的依赖。在Indigo 1 x 1 Base数据集上，该方法在多类别真伪评估中优于传统及适配的生成基线，且无需伪造样本训练或阈值校准。
原文摘要 · Abstract (English)
Reconstruction-based generative models offer a natural framework for unsupervised out-of-distribution (OOD) detection, but multi-class normality modelling requires a single detector to capture multiple in-distribution manifolds and produce comparable anomaly scores across classes. We study this problem in copy detection pattern (CDP) authentication, where authentic and counterfeit samples are visually similar but differ in subtle printing-and-digitisation (P&D) signatures. We propose a diffusion-based multi-class normality framework in which a single class-conditional ControlNet is trained exclusively on authentic CDPs from multiple P&D classes and detects counterfeits through reconstruction error under authentic-class conditioning. We further introduce dual template masking, which hides complementary regions of the input template and scores only withheld pixels, reducing reliance on visible binary structure. On the Indigo 1 x 1 Base dataset, the proposed method outperforms traditional and adapted generative baselines under multi-class authentic-versus-counterfeit evaluation, without using counterfeit samples for training or threshold calibration.
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。