The presence of a bias in each image data collection has recently attracted a lot of attention in the computer vision community showing the limits in generalization of any learning method trained on a specific dataset. At the same time, with the rapid development of deep learning architectures, the activation values of Convolutional Neural Networks (CNN) are emerging as reliable and robust image descriptors. In this paper we propose to verify the potential of the DeCAF features when facing the dataset bias problem. We conduct a series of analyses looking at how existing datasets differ among each other and verifying the performance of existing debiasing methods under different representations. We learn important lessons on which part of the dataset bias problem can be considered solved and which open questions still need to be tackled. © Springer International Publishing Switzerland 2015.

A deeper look at dataset bias / Tommasi, Tatiana; Patricia, Novi; Caputo, Barbara; Tuytelaars, Tinne. - 9358:(2015), pp. 504-516. (Intervento presentato al convegno 37th German Conference on Pattern Recognition, GCPR 2015 tenutosi a Aachen; Germany) [10.1007/978-3-319-24947-6_42].

A deeper look at dataset bias

TOMMASI, TATIANA
;
PATRICIA, NOVI;CAPUTO, BARBARA;
2015

Abstract

The presence of a bias in each image data collection has recently attracted a lot of attention in the computer vision community showing the limits in generalization of any learning method trained on a specific dataset. At the same time, with the rapid development of deep learning architectures, the activation values of Convolutional Neural Networks (CNN) are emerging as reliable and robust image descriptors. In this paper we propose to verify the potential of the DeCAF features when facing the dataset bias problem. We conduct a series of analyses looking at how existing datasets differ among each other and verifying the performance of existing debiasing methods under different representations. We learn important lessons on which part of the dataset bias problem can be considered solved and which open questions still need to be tackled. © Springer International Publishing Switzerland 2015.
2015
37th German Conference on Pattern Recognition, GCPR 2015
Theoretical Computer Science; Computer Science (all)
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
A deeper look at dataset bias / Tommasi, Tatiana; Patricia, Novi; Caputo, Barbara; Tuytelaars, Tinne. - 9358:(2015), pp. 504-516. (Intervento presentato al convegno 37th German Conference on Pattern Recognition, GCPR 2015 tenutosi a Aachen; Germany) [10.1007/978-3-319-24947-6_42].
File allegati a questo prodotto
File Dimensione Formato  
Tommasi_A-Deeper-Look_2015.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.07 MB
Formato Adobe PDF
1.07 MB 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/11573/910657
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 24
  • ???jsp.display-item.citation.isi??? 24
social impact