This paper investigates the effectiveness of deep learning (DL) for domain adaptation (DA) problems in the classification of remote sensing images to generate land-cover maps. To this end, we introduce two different DL architectures: 1) single-stage domain adaptation (SS-DA) architecture; and 2) hierarchal domain adaptation (H-DA) architecture. Both architectures require that a reliable training set is available only for one of the images (i.e., the source domain) from a previous analysis, whereas it is not for another image to be classified (i.e., the target domain). To classify the target domain image, the proposed architectures aim to learn a shared feature representation that is invariant across the source and target domains in a completely unsupervised fashion. To this end, both architectures are defined based on based on the stacked denoising auto-encoders (SDAEs) due to their high capability to define high-level feature representations. The SS-DA architecture leads to a common feature space by: 1) initially unifying the samples in source and target domains; and 2) then feeding them simultaneously into the SDAE. To further increase the robustness of the shared representations, the H-DA employs: 1) two SDAEs for learning independently the high level representations of source and target domains; and 2) a consensus SDAE to learn the domain invariant high-level features features. After obtaining the domain invariant features through proposed architectures, the classifier is training by the domain invariant source domain labeled samples, and then the domain invariant target domain samples are classified to generate the related classification map. Experimental results obtained in the classification of very high resolution images confirm the effectiveness of the proposed DL architectures.

Domain adaptation based on deep denoising auto-encoders for classification of remote sensing images / Riz, Emanuele; Demir, Begum; Bruzzone, Lorenzo. - ELETTRONICO. - 10004:(2016). ((Intervento presentato al convegno SPIE Remote Sensing 2016 tenutosi a Edinburgh, United Kingdom nel 26th-28th September 2016 [10.1117/12.2241982].

Domain adaptation based on deep denoising auto-encoders for classification of remote sensing images

Demir, Begum;Bruzzone, Lorenzo
2016

Abstract

This paper investigates the effectiveness of deep learning (DL) for domain adaptation (DA) problems in the classification of remote sensing images to generate land-cover maps. To this end, we introduce two different DL architectures: 1) single-stage domain adaptation (SS-DA) architecture; and 2) hierarchal domain adaptation (H-DA) architecture. Both architectures require that a reliable training set is available only for one of the images (i.e., the source domain) from a previous analysis, whereas it is not for another image to be classified (i.e., the target domain). To classify the target domain image, the proposed architectures aim to learn a shared feature representation that is invariant across the source and target domains in a completely unsupervised fashion. To this end, both architectures are defined based on based on the stacked denoising auto-encoders (SDAEs) due to their high capability to define high-level feature representations. The SS-DA architecture leads to a common feature space by: 1) initially unifying the samples in source and target domains; and 2) then feeding them simultaneously into the SDAE. To further increase the robustness of the shared representations, the H-DA employs: 1) two SDAEs for learning independently the high level representations of source and target domains; and 2) a consensus SDAE to learn the domain invariant high-level features features. After obtaining the domain invariant features through proposed architectures, the classifier is training by the domain invariant source domain labeled samples, and then the domain invariant target domain samples are classified to generate the related classification map. Experimental results obtained in the classification of very high resolution images confirm the effectiveness of the proposed DL architectures.
Image and Signal Processing for Remote Sensing 22
Bellingham, WA
SPIE
9781510604124
9781510604131
Riz, Emanuele; Demir, Begum; Bruzzone, Lorenzo
Domain adaptation based on deep denoising auto-encoders for classification of remote sensing images / Riz, Emanuele; Demir, Begum; Bruzzone, Lorenzo. - ELETTRONICO. - 10004:(2016). ((Intervento presentato al convegno SPIE Remote Sensing 2016 tenutosi a Edinburgh, United Kingdom nel 26th-28th September 2016 [10.1117/12.2241982].
File in questo prodotto:
File Dimensione Formato  
SPIEDARizDemirBruzzone.pdf

Solo gestori archivio

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 330.03 kB
Formato Adobe PDF
330.03 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: http://hdl.handle.net/11572/168519
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 6
social impact