PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization
This work addresses the problem of efficiently detecting and localizing anomalies in industrial visual inspection, offering a low-complexity solution for manufacturers.
This paper introduces PaDiM, a framework for one-class anomaly detection and localization in images. It leverages a pretrained CNN for patch embedding and multivariate Gaussian distributions to model the normal class, achieving state-of-the-art performance on the MVTec AD and STC datasets.
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.