Most domain adaptation methods consider the problem of transferring knowledge to the target domain from a single-source dataset. However, in practical applications, we typically have access to multiple sources. In this paper we propose the first approach for multi-source domain adaptation (MSDA) based on generative adversarial networks. Our method is inspired by the observation that the appearance of a given image depends on three factors: the domain, the style (characterized in terms of low-level features variations) and the content. For this reason, we propose to project the source image features onto a space where only the dependence from the content is kept, and then re-project this invariant representation onto the pixel space using the target domain and style. In this way, new labeled images can be generated which are used to train a final target classifier. We test our approach using common MSDA benchmarks, showing that it outperforms state-of-the-art methods.

TriGAN: image-to-image translation for multi-source domain adaptation / Roy, S.; Siarohin, A.; Sangineto, E.; Sebe, N.; Ricci, E.. - In: MACHINE VISION AND APPLICATIONS. - ISSN 0932-8092. - 32:1(2021), pp. 4101-4112. [10.1007/s00138-020-01164-4]

TriGAN: image-to-image translation for multi-source domain adaptation

Roy S.;Siarohin A.;Sangineto E.;Sebe N.;Ricci E.
2021-01-01

Abstract

Most domain adaptation methods consider the problem of transferring knowledge to the target domain from a single-source dataset. However, in practical applications, we typically have access to multiple sources. In this paper we propose the first approach for multi-source domain adaptation (MSDA) based on generative adversarial networks. Our method is inspired by the observation that the appearance of a given image depends on three factors: the domain, the style (characterized in terms of low-level features variations) and the content. For this reason, we propose to project the source image features onto a space where only the dependence from the content is kept, and then re-project this invariant representation onto the pixel space using the target domain and style. In this way, new labeled images can be generated which are used to train a final target classifier. We test our approach using common MSDA benchmarks, showing that it outperforms state-of-the-art methods.
2021
1
Roy, S.; Siarohin, A.; Sangineto, E.; Sebe, N.; Ricci, E.
TriGAN: image-to-image translation for multi-source domain adaptation / Roy, S.; Siarohin, A.; Sangineto, E.; Sebe, N.; Ricci, E.. - In: MACHINE VISION AND APPLICATIONS. - ISSN 0932-8092. - 32:1(2021), pp. 4101-4112. [10.1007/s00138-020-01164-4]
File in questo prodotto:
File Dimensione Formato  
MVAP21.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 1.13 MB
Formato Adobe PDF
1.13 MB Adobe PDF Visualizza/Apri

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/11572/326156
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 7
  • OpenAlex ND
social impact