Image anomaly detection is an application-driven problem where the aim is to identify novel samples, which differ significantly from the normal ones. We here propose Pyramidal Image Anomaly DEtector (PIADE), a deep reconstruction-based pyramidal approach, in which image features are extracted at different scale levels to better catch the peculiarities that could help to discriminate between normal and anomalous data. The features are dynamically routed to a reconstruction layer and anomalies can be identified by comparing the input image with its reconstruction. Unlike similar approaches, the comparison is done by using structural similarity and perceptual loss rather than trivial pixel-by-pixel comparison. The proposed method performed at par or better than the state-of-the-art methods when tested on publicly available datasets such as CIFAR10, COIL-100 and MVTec.

A Neural Network for Image Anomaly Detection with Deep Pyramidal Representations and Dynamic Routing

Mishra P.;Piciarelli C.;Foresti G. L.
2020

Abstract

Image anomaly detection is an application-driven problem where the aim is to identify novel samples, which differ significantly from the normal ones. We here propose Pyramidal Image Anomaly DEtector (PIADE), a deep reconstruction-based pyramidal approach, in which image features are extracted at different scale levels to better catch the peculiarities that could help to discriminate between normal and anomalous data. The features are dynamically routed to a reconstruction layer and anomalies can be identified by comparing the input image with its reconstruction. Unlike similar approaches, the comparison is done by using structural similarity and perceptual loss rather than trivial pixel-by-pixel comparison. The proposed method performed at par or better than the state-of-the-art methods when tested on publicly available datasets such as CIFAR10, COIL-100 and MVTec.
File in questo prodotto:
File Dimensione Formato  
manuscript.pdf

accesso aperto

Tipologia: Documento in Pre-print
Licenza: Creative commons
Dimensione 1.84 MB
Formato Adobe PDF
1.84 MB Adobe PDF Visualizza/Apri
paper_no_highlishts.pdf

embargo fino al 31/10/2021

Tipologia: Documento in Post-print
Licenza: Creative commons
Dimensione 1.98 MB
Formato Adobe PDF
1.98 MB Adobe PDF Visualizza/Apri
S0129065720500604.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Non pubblico
Dimensione 2.01 MB
Formato Adobe PDF
2.01 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11390/1190871
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 21
  • ???jsp.display-item.citation.isi??? 22
social impact