Visualization for Multivariate Gaussian Anomaly Detection in Images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Visualization for Multivariate Gaussian Anomaly Detection in Images

Résumé

This paper introduces a simplified variation of the PaDiM (Pixel-Wise Anomaly Detection through Instance Modeling) method for anomaly detection in images, fitting a single multivariate Gaussian (MVG) distribution to the feature vectors extracted from a backbone convolutional neural network (CNN) and using their Mahalanobis distance as the anomaly score. We introduce an intermediate step in this framework by applying a whitening transformation to the feature vectors, which enables the generation of heatmaps capable of visually explaining the features learned by the MVG. The proposed technique is evaluated on the MVTec-AD dataset, and the results show the importance of visual model validation, providing insights into issues in this framework that were otherwise invisible. The visualizations generated for this paper are publicly available at https://doi.org/10.5281/zenodo.7937978.

Dates et versions

hal-04319304 , version 1 (02-12-2023)

Licence

Paternité - Partage selon les Conditions Initiales

Identifiants

Citer

João P C Bertoldo, David Arrustico. Visualization for Multivariate Gaussian Anomaly Detection in Images. 2023 Twelfth International Conference on Image Processing Theory, Tools and Applications (IPTA), Oct 2023, Paris, France. ⟨10.1109/IPTA59101.2023.10320060⟩. ⟨hal-04319304⟩
22 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More