基于跨模态特征映射的多模态工业异常检测
Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping
AI总结：
针对工业多模态异常检测任务，提出轻量快速的跨模态特征映射框架及层剪枝技术，在MVTec 3D-AD数据集上实现了更优性能与更高效率。
摘要：
本文研究工业多模态异常检测（AD）任务，该任务利用点云和RGB图像定位异常。我们提出了一种新颖的轻量快速框架，该框架学习在正常样本上将一种模态的特征映射到另一种模态。测试时，通过定位观测特征与映射特征之间的不一致来检测异常。大量实验表明，我们的方法在MVTec 3D-AD数据集的标准设置和少样本设置下均实现了最优的检测和分割性能，同时相比以往的多模态AD方法推理速度更快、内存占用更少。此外，我们提出了一种层剪枝技术，可在性能牺牲极小的情况下提升内存和时间效率。
英文摘要：
The paper explores the industrial multimodal Anomaly Detection (AD) task, which exploits point clouds and RGB images to localize anomalies. We introduce a novel light and fast framework that learns to map features from one modality to the other on nominal samples. At test time, anomalies are detected by pinpointing inconsistencies between observed and mapped features. Extensive experiments show that our approach achieves state-of-the-art detection and segmentation performance in both the standard and few-shot settings on the MVTec 3D-AD dataset while achieving faster inference and occupying less memory than previous multimodal AD methods. Moreover, we propose a layer-pruning technique to improve memory and time efficiency with a marginal sacrifice in performance.
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。
