The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and target domains. Alleviating the domain shift problem, especially in the challenging setting where no labeled data are available for the target domain, is paramount for having visual recognition systems working in the wild. As the problem stems from a shift among distributions, intuitively one should try to align them. In the literature, this has resulted in a stream of works attempting to align the feature representations learned from the source and target domains. Here we take a different route. Rather than introducing regularization terms aiming to promote the alignment of the two representations, we act at the distribution level through the introduction of \emphDomaIn Alignment Layers (\DIAL), able to match the observed source and target data distributions to a reference one. Thorough experiments on three different public benchmarks we confirm the power of our approach.

Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation / Carlucci, FABIO MARIA; Porzi, Lorenzo; Caputo, Barbara; Ricci, Elisa; ROTA BULO', Samuel. - ELETTRONICO. - 1:(2017), pp. 87-100. (Intervento presentato al convegno International Conference on Image Analysis and Processing tenutosi a Catania, ITALY) [10.1007/978-3-319-68560-1_32].

Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation

Fabio Maria Carlucci
;
Lorenzo Porzi;Barbara Caputo;Elisa Ricci;Samuel Rota Bulò
2017

Abstract

The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and target domains. Alleviating the domain shift problem, especially in the challenging setting where no labeled data are available for the target domain, is paramount for having visual recognition systems working in the wild. As the problem stems from a shift among distributions, intuitively one should try to align them. In the literature, this has resulted in a stream of works attempting to align the feature representations learned from the source and target domains. Here we take a different route. Rather than introducing regularization terms aiming to promote the alignment of the two representations, we act at the distribution level through the introduction of \emphDomaIn Alignment Layers (\DIAL), able to match the observed source and target data distributions to a reference one. Thorough experiments on three different public benchmarks we confirm the power of our approach.
2017
International Conference on Image Analysis and Processing
computer science; computer vision and pattern recognition; computer vision and pattern recognition
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation / Carlucci, FABIO MARIA; Porzi, Lorenzo; Caputo, Barbara; Ricci, Elisa; ROTA BULO', Samuel. - ELETTRONICO. - 1:(2017), pp. 87-100. (Intervento presentato al convegno International Conference on Image Analysis and Processing tenutosi a Catania, ITALY) [10.1007/978-3-319-68560-1_32].
File allegati a questo prodotto
File Dimensione Formato  
Carlucci_Just_2017.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 571.65 kB
Formato Adobe PDF
571.65 kB Adobe PDF   Contatta l'autore
Carlucci_copertina-frontespizio_Just_2017.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 282.02 kB
Formato Adobe PDF
282.02 kB Adobe PDF   Contatta l'autore
Carlucci_indice_Just_2017.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 225.13 kB
Formato Adobe PDF
225.13 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/11573/1016398
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 24
  • ???jsp.display-item.citation.isi??? 18
social impact