Deep Random Projection Outlyingness for Unsupervised Anomaly Detection - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Deep Random Projection Outlyingness for Unsupervised Anomaly Detection

Résumé

Random projection is a common technique for designing algorithms in a variety of areas, including information retrieval, compressive sensing and measuring of outlyingness. In this work, the original random projection outlyingness measure is modified and associated with a neural network to obtain an unsupervised anomaly detection method able to handle multimodal normality. Theoretical and experimental arguments are presented to justify the choices of the anomaly score estimator, the dimensions of the random projections, and the number of such projections. The contribution of adapted dropouts is investigated, along with the affine stability of the proposed method. The performance of the proposed neural network approach is comparable to a state-of-the-art anomaly detection method. Experiments conducted on the MNIST, Fashion-MNIST and CIFAR-10 datasets show the relevance of the proposed approach, and suggest a possible extension to a semi-supervised setup.
Fichier principal
Vignette du fichier
preprint_v6_HAL.pdf (982.27 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03203686 , version 1 (07-06-2021)
hal-03203686 , version 2 (26-07-2021)

Identifiants

Citer

Martin Bauw, Santiago Velasco-Forero, Jesus Angulo, Claude Adnet, Olivier Airiau. Deep Random Projection Outlyingness for Unsupervised Anomaly Detection. 2021. ⟨hal-03203686v1⟩
476 Consultations
173 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More