PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization

• Published in: Lecture notes in computer science Vol. 12664; pp. 475 - 489
• Main Authors: Defard, Thomas, Setkov, Aleksandr, Loesch, Angelique, Audigier, Romaric
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2021; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Anomaly detection; Anomaly localization; Computer vision
• ISBN: 9783030687984; 3030687988
• ISSN: 0302-9743; 1611-3349; 1611-3349
• DOI: 10.1007/978-3-030-68799-1_35

We present a new framework for Patch Distribution Modeling, PaDiM, to concurrently detect and localize anomalies in images in a one-class learning setting. PaDiM makes use of a pretrained convolutional neural network (CNN) for patch embedding, and of multivariate Gaussian distributions to get a probabilistic representation of the normal class. It also exploits correlations between the different semantic levels of CNN to better localize anomalies. PaDiM outperforms current state-of-the-art approaches for both anomaly detection and localization on the MVTec AD and STC datasets. To match real-world visual industrial inspection, we extend the evaluation protocol to assess performance of anomaly localization algorithms on non-aligned dataset. The state-of-the-art performance and low complexity of PaDiM make it a good candidate for many industrial applications.