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 chapter we propose to verify the potential of the CNN features when facing the dataset bias problem. With this purpose we introduce a large testbed for cross-dataset analysis and we discuss the challenges faced to create two comprehensive experimental setups by aligning twelve existing image databases. We conduct a series of analyses looking at how the 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 AG 2017.

A Deeper Look at Dataset Bias / Tommasi, Tatiana; Patricia, Novi; Caputo, Barbara; Tuytelaars, Tinne. - (2017), pp. 37-55. - ADVANCES IN COMPUTER VISION AND PATTERN RECOGNITION. [10.1007/978-3-319-58347-1_2].

A Deeper Look at Dataset Bias

Tommasi, Tatiana
;
Patricia, Novi;Caputo, Barbara;
2017

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 chapter we propose to verify the potential of the CNN features when facing the dataset bias problem. With this purpose we introduce a large testbed for cross-dataset analysis and we discuss the challenges faced to create two comprehensive experimental setups by aligning twelve existing image databases. We conduct a series of analyses looking at how the 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 AG 2017.
2017
Domain Adaptation in Computer Vision Applications
978-3-319-58346-4
978-3-319-58347-1
Computer Science; Artificial Intelligence; Computer Science; Theory & Methods
02 Pubblicazione su volume::02a Capitolo o Articolo
A Deeper Look at Dataset Bias / Tommasi, Tatiana; Patricia, Novi; Caputo, Barbara; Tuytelaars, Tinne. - (2017), pp. 37-55. - ADVANCES IN COMPUTER VISION AND PATTERN RECOGNITION. [10.1007/978-3-319-58347-1_2].
File allegati a questo prodotto
File Dimensione Formato  
Tommasi_A-Deeper-Look _2017.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.52 MB
Formato Adobe PDF
1.52 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/11573/1097305
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 182
  • ???jsp.display-item.citation.isi??? ND
social impact