The ability to categorize is a cornerstone of visual intelligence, and a key functionality for artificial, autonomous visual machines. This problem will never be solved without algorithms able to adapt and generalize across visual domains. Within the context of domain adaptation and generalization, this paper focuses on the predictive domain adaptation scenario, namely the case where no target data are available and the system has to learn to generalize from annotated source images plus unlabeled samples with associated metadata from auxiliary domains. Our contribution is the first deep architecture that tackles predictive domain adaptation, able to leverage over the information brought by the auxiliary domains through a graph. Moreover, we present a simple yet effective strategy that allows us to take advantage of the incoming target data at test time, in a continuous domain adaptation scenario. Experiments on three benchmark databases support the value of our approach.

AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs / Mancini, Massimiliano; Bulo, Samuel Rota; Caputo, Barbara; Ricci, Elisa. - (2019), pp. 6561-6570. (Intervento presentato al convegno CVPR tenutosi a Long Beach, CA, USA nel 15-20 June 2019) [10.1109/CVPR.2019.00673].

AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs

Mancini, Massimiliano;Bulo, Samuel Rota;Ricci, Elisa
2019-01-01

Abstract

The ability to categorize is a cornerstone of visual intelligence, and a key functionality for artificial, autonomous visual machines. This problem will never be solved without algorithms able to adapt and generalize across visual domains. Within the context of domain adaptation and generalization, this paper focuses on the predictive domain adaptation scenario, namely the case where no target data are available and the system has to learn to generalize from annotated source images plus unlabeled samples with associated metadata from auxiliary domains. Our contribution is the first deep architecture that tackles predictive domain adaptation, able to leverage over the information brought by the auxiliary domains through a graph. Moreover, we present a simple yet effective strategy that allows us to take advantage of the incoming target data at test time, in a continuous domain adaptation scenario. Experiments on three benchmark databases support the value of our approach.
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Piscataway, NJ USA
IEEE
978-1-7281-3293-8
Mancini, Massimiliano; Bulo, Samuel Rota; Caputo, Barbara; Ricci, Elisa
AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs / Mancini, Massimiliano; Bulo, Samuel Rota; Caputo, Barbara; Ricci, Elisa. - (2019), pp. 6561-6570. (Intervento presentato al convegno CVPR tenutosi a Long Beach, CA, USA nel 15-20 June 2019) [10.1109/CVPR.2019.00673].
File in questo prodotto:
File Dimensione Formato  
08954389.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 376.69 kB
Formato Adobe PDF
376.69 kB 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/11572/251264
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 49
  • ???jsp.display-item.citation.isi??? 37
social impact