Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbor (NBNN)-based classifiers have lost momentum in the community. This is because (1) such algorithms cannot use CNN activations as input features, (2) they cannot be used as final layer of CNN architectures for end-to-end training, and (3) they are generally not scalable and hence cannot handle big data. This paper proposes a framework that addresses all these issues, thus bringing back NBNNs on the map. We solve the first by extracting CNN activations from local patches at multiple scale levels, similarly to [13]. We address simultaneously the second and third by proposing a scalable version of Naive Bayes Non-linear Learning (NBNL, [7]). Results obtained using pre-trained CNNs on standard scene and domain adaptation databases show the strength of our approach, opening a new season for NBNNs. © 2016 IEEE.

When Naïve bayes nearest neighbors meet convolutional neural networks / Kuzborskij, Ilja; Carlucci, FABIO MARIA; Caputo, Barbara. - (2016), pp. 2100-2109. (Intervento presentato al convegno 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016; ; 26 June 2016 through 1 July 2016; Category numberE5869; Code 125363 tenutosi a Las Vegas; United States).

When Naïve bayes nearest neighbors meet convolutional neural networks

KUZBORSKIJ, ILJA
;
CARLUCCI, FABIO MARIA
;
CAPUTO, BARBARA
2016

Abstract

Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbor (NBNN)-based classifiers have lost momentum in the community. This is because (1) such algorithms cannot use CNN activations as input features, (2) they cannot be used as final layer of CNN architectures for end-to-end training, and (3) they are generally not scalable and hence cannot handle big data. This paper proposes a framework that addresses all these issues, thus bringing back NBNNs on the map. We solve the first by extracting CNN activations from local patches at multiple scale levels, similarly to [13]. We address simultaneously the second and third by proposing a scalable version of Naive Bayes Non-linear Learning (NBNL, [7]). Results obtained using pre-trained CNNs on standard scene and domain adaptation databases show the strength of our approach, opening a new season for NBNNs. © 2016 IEEE.
2016
29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016; ; 26 June 2016 through 1 July 2016; Category numberE5869; Code 125363
Big data; Chemical activation; Classifiers; Computer vision; Convolution; Neural networks
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
When Naïve bayes nearest neighbors meet convolutional neural networks / Kuzborskij, Ilja; Carlucci, FABIO MARIA; Caputo, Barbara. - (2016), pp. 2100-2109. (Intervento presentato al convegno 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016; ; 26 June 2016 through 1 July 2016; Category numberE5869; Code 125363 tenutosi a Las Vegas; United States).
File allegati a questo prodotto
File Dimensione Formato  
Kuzborskij_Postprint_When-Naïve-Bayes_2016.pdf

accesso aperto

Note: https://ieeexplore.ieee.org/document/7780600
Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 919.31 kB
Formato Adobe PDF
919.31 kB Adobe PDF
Kuzborskij_When-Naïve-Bayes_2016.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 585.81 kB
Formato Adobe PDF
585.81 kB Adobe PDF   Contatta l'autore

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/11573/911189
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 21
  • ???jsp.display-item.citation.isi??? 15
social impact