Novelty detection is commonly referred to as the discrimination of observations that do not conform to a learned model of regularity. Despite its importance in different application settings, designing a novelty detector is utterly complex due to the unpredictable nature of novelties and its inaccessibility during the training procedure, factors which expose the unsupervised nature of the problem. In our proposal, we design a general framework where we equip a deep autoencoder with a parametric density estimator that learns the probability distribution underlying its latent representations through an autoregressive procedure. We show that a maximum likelihood objective, optimized in conjunction with the reconstruction of normal samples, effectively acts as a regularizer for the task at hand, by minimizing the differential entropy of the distribution spanned by latent vectors. In addition to providing a very general formulation, extensive experiments of our model on publicly available datasets deliver on-par or superior performances if compared to state-of-the-art methods in one-class and video anomaly detection settings. Differently from prior works, our proposal does not make any assumption about the nature of the novelties, making our work readily applicable to diverse contexts.

Latent Space Autoregression for Novelty Detection / Abati, Davide; Porrello, Angelo; Calderara, Simone; Cucchiara, Rita. - (2019), pp. 481-490. ((Intervento presentato al convegno International Conference on Computer Vision and Pattern Recognition tenutosi a Long Beach, CA nel 16-20 June 2019 [10.1109/CVPR.2019.00057].

Latent Space Autoregression for Novelty Detection

ABATI, DAVIDE;PORRELLO, ANGELO;Simone Calderara;Rita Cucchiara
2019

Abstract

Novelty detection is commonly referred to as the discrimination of observations that do not conform to a learned model of regularity. Despite its importance in different application settings, designing a novelty detector is utterly complex due to the unpredictable nature of novelties and its inaccessibility during the training procedure, factors which expose the unsupervised nature of the problem. In our proposal, we design a general framework where we equip a deep autoencoder with a parametric density estimator that learns the probability distribution underlying its latent representations through an autoregressive procedure. We show that a maximum likelihood objective, optimized in conjunction with the reconstruction of normal samples, effectively acts as a regularizer for the task at hand, by minimizing the differential entropy of the distribution spanned by latent vectors. In addition to providing a very general formulation, extensive experiments of our model on publicly available datasets deliver on-par or superior performances if compared to state-of-the-art methods in one-class and video anomaly detection settings. Differently from prior works, our proposal does not make any assumption about the nature of the novelties, making our work readily applicable to diverse contexts.
International Conference on Computer Vision and Pattern Recognition
Long Beach, CA
16-20 June 2019
481
490
Abati, Davide; Porrello, Angelo; Calderara, Simone; Cucchiara, Rita
Latent Space Autoregression for Novelty Detection / Abati, Davide; Porrello, Angelo; Calderara, Simone; Cucchiara, Rita. - (2019), pp. 481-490. ((Intervento presentato al convegno International Conference on Computer Vision and Pattern Recognition tenutosi a Long Beach, CA nel 16-20 June 2019 [10.1109/CVPR.2019.00057].
File in questo prodotto:
File Dimensione Formato  
Autoregression(2).pdf

accesso aperto

Tipologia: Post-print dell'autore (bozza post referaggio)
Dimensione 8.78 MB
Formato Adobe PDF
8.78 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11380/1173698
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 150
  • ???jsp.display-item.citation.isi??? 114
social impact