1 Introduction
1.1 What is AD?


Fig 1, 2 of MVTec AD, cvpr19
1.2 Applications
1.2.1 industrial inspection
-
集成电路领域的陶瓷封装基板CPS3D-Seg, AAAI26
-
环状变压器线圈

-
finding defects of objects or materials on industrial production lines [5, 7, 10, 15, 36, 56, 62, 76] — SSPCAB, cvpr22
1.2.2 public security
detecting abnormal events such as traffic accidents, fights, explosions, etc. [12, 13, 17–19, 27, 28, 33, 39, 41, 47–50, 52, 67, 72, 73, 77, 78]. — SSPCAB, cvpr22


fig 6 & 8 of SSPCAB, cvpr22
1.3 The problem
- fundamental principle: modeling normality in the training data and assessing whether a test image aligns with this learned normality (常态/正常性).
- also pursued as a one-class classification (outlier detection) problem
- The nature of AD problem: unsupervised + the restricted data access (the |normal sample| for training is not often large enough, 60 — 200, even k-shot or zero-shot)
- “Since abnormal samples are available only at test time, supervised learning methods are not directly applicable to anomaly detection.” is it true? Yes, in most case.
- Learn normality via feature embedding or reconstruction based methods