FastRef：用于少样本工业异常检测的快速原型细化
FastRef:Fast Prototype Refinement for Few-Shot Industrial Anomaly Detection
AI总结：
针对少样本工业异常检测中原型代表性不足的问题，提出高效原型细化框架FastRef，通过迭代执行特征转移与异常抑制优化原型，实验证明其在多个基准数据集上有效且计算高效。
摘要：
少样本工业异常检测（FS-IAD）对在数据稀缺环境中运行的实际自动检测系统提出了关键挑战。现有方法主要侧重于从有限的正常样本中提取原型，通常忽略了系统地结合查询图像统计信息来增强原型的代表性。为解决此问题，我们提出FastRef，一种用于FS-IAD的新型高效原型细化框架。该方法通过迭代的两阶段过程运行：（1）通过可优化的变换矩阵将查询特征的特征转移到原型中；（2）通过原型对齐进行异常抑制。特征转移通过原型的查询特征线性重建实现，而异常抑制解决了FS-IAD中的一个关键观察，即与拥有大量正常原型的传统IAD不同，有限样本设置使异常重建更有可能发生。因此，我们对非高斯采样特征采用最优传输（OT）来测量并最小化原型与其细化对应物之间的差距以实现异常抑制。为进行全面评估，我们将FastRef与三种基于原型的竞争性FS-IAD方法集成：PatchCore、FastRecon、WinCLIP和AnomalyDINO。在MVTec、ViSA、MPDD和RealIAD四个基准数据集上的广泛实验表明，我们的方法在1/2/4-shots下均具备有效性和计算效率。
英文摘要：
Few-shot industrial anomaly detection (FS-IAD) presents a critical challenge for practical automated inspection systems operating in data-scarce environments. While existing approaches predominantly focus on deriving prototypes from limited normal samples, they typically neglect to systematically incorporate query image statistics to enhance prototype representativeness. To address this issue, we propose FastRef, a novel and efficient prototype refinement framework for FS-IAD. Our method operates through an iterative two-stage process: (1) characteristic transfer from query features to prototypes via an optimizable transformation matrix, and (2) anomaly suppression through prototype alignment. The characteristic transfer is achieved through linear reconstruction of query features from prototypes, while the anomaly suppression addresses a key observation in FS-IAD that unlike conventional IAD with abundant normal prototypes, the limited-sample setting makes anomaly reconstruction more probable. Therefore, we employ optimal transport (OT) for non-Gaussian sampled features to measure and minimize the gap between prototypes and their refined counterparts for anomaly suppression. For comprehensive evaluation, we integrate FastRef with three competitive prototype-based FS-IAD methods: PatchCore, FastRecon, WinCLIP, and AnomalyDINO. Extensive experiments across four benchmark datasets of MVTec, ViSA, MPDD and RealIAD demonstrate both the effectiveness and computational efficiency of our approach under 1/2/4-shots.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
