基于扩散合成与特征挖掘的工业图像异常检测
卜玉真,余家斌,马道滨,陈梁宇,孙龙,杨力,章东平

Industrial image anomaly detection via diffusion synthesis and feature mining
Yuzhen BU,Jiabin YU,Daobin MA,Liangyu CHEN,Long SUN,Li YANG,Dongping ZHANG
表 3 不同异常检测方法在MVTec AD数据集上的整体性能对比
Tab.3 Overall performance comparison of different anomaly detection methods on MVTec AD dataset
方法Image AUROC/%Pixel AUROC/%
PatchCore99.198.1
SimpleNet99.698.1
FastFlow99.398.1
DRAEM+SSPCAB98.997.2
UniAD96.696.6
RD++99.498.3
DeSTSeg98.697.9
DiffAD98.798.3
RealNet99.699.0
本研究算法99.799.0