HVA-CLIP: Hierarchical Visual-Semantic Alignment for Zero-Shot Anomaly Detection
收藏IEEE2026-04-17 收录
下载链接：
https://ieee-dataport.org/documents/hva-clip-hierarchical-visual-semantic-alignment-zero-shot-anomaly-detection
下载链接
链接失效反馈官方服务：
资源简介：
MVTec AD is a dataset for benchmarking anomaly detection methods with a focus on industrial inspection. It contains over 5000 high-resolution images divided into fifteen different object and texture categories. Each category comprises a set of defect-free training images and a test set of images with various kinds of defects as well as images without defects.
提供机构：
Lijian Fan
