The ability to generalize across visual domains is crucial for the robustness of artificial recognition systems. Although many training sources may be available in real contexts, the access to even unlabeled target samples cannot be taken for granted, which makes standard unsupervised domain adaptation methods inapplicable in the wild. In this work we investigate how to exploit multiple sources by hallucinating a deep visual domain composed of images, possibly unrealistic, able to maintain categorical knowledge while discarding specific source styles. The produced agnostic images are the result of a deep architecture that applies pixel adaptation on the original source data guided by two adversarial domain classifier branches at image and feature level. Our approach is conceived to learn only from source data, but it seamlessly extends to the use of unlabeled target samples. Remarkable results for both multi-source domain adaptation and domain generalization support the power of hallucinating agnostic images in this framework.
Hallucinating Agnostic Images to Generalize Across Domains / Carlucci, Fm; Russo, P; Tommasi, T; Caputo, B. - (2019), pp. 3227-3234. (Intervento presentato al convegno 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) tenutosi a Seoul, Korea) [10.1109/ICCVW.2019.00403].
Hallucinating Agnostic Images to Generalize Across Domains
Carlucci, FM
Primo
Investigation
;Russo, PSecondo
Conceptualization
;Tommasi, TPenultimo
Conceptualization
;Caputo, BUltimo
Conceptualization
2019
Abstract
The ability to generalize across visual domains is crucial for the robustness of artificial recognition systems. Although many training sources may be available in real contexts, the access to even unlabeled target samples cannot be taken for granted, which makes standard unsupervised domain adaptation methods inapplicable in the wild. In this work we investigate how to exploit multiple sources by hallucinating a deep visual domain composed of images, possibly unrealistic, able to maintain categorical knowledge while discarding specific source styles. The produced agnostic images are the result of a deep architecture that applies pixel adaptation on the original source data guided by two adversarial domain classifier branches at image and feature level. Our approach is conceived to learn only from source data, but it seamlessly extends to the use of unlabeled target samples. Remarkable results for both multi-source domain adaptation and domain generalization support the power of hallucinating agnostic images in this framework.File | Dimensione | Formato | |
---|---|---|---|
Carlucci_Hallucinating-Agnostic_2019.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
378.27 kB
Formato
Adobe PDF
|
378.27 kB | Adobe PDF | |
Carlucci_preprint_Hallucinating-Agnostic_2019.pdf.pdf
accesso aperto
Tipologia:
Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza:
Creative commons
Dimensione
1.76 MB
Formato
Adobe PDF
|
1.76 MB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.