This paper presents a kernel-based feature selection method for the classification of hyperspectral images. The proposed method aims at selecting a subset of the original features that are both 1) relevant (discriminant) for the considered classification problem, i.e., preserve the functional relationship between input and output variables, and 2) invariant (stable) across different domains, i.e., minimize the data-set shift between the source and the target domains. Domains can be associated with hyperspectral images collected either on different geographical areas or on the same area at different times. We propose a novel measure of data-set shift for evaluating the domain stability, which computes the distance of the conditional distributions between the source and target domains in a reproducing kernel Hilbert space. Such a measure is defined on the basis of the kernel embeddings of the conditional distributions resulting in a nonparametric approach that does not require estimating the distribution of the classes. The adopted search strategy is based on a multiobjective optimization algorithm, which optimizes the two terms of the criterion function for the estimation of the Pareto-optimal solutions. This results in an effective approach of performing feature selection in a transfer learning setting. The experimental results obtained on two hyperspectral images show the effectiveness of the proposed method in selecting features with high generalization capabilities.

Kernel-Based Domain-Invariant Feature Selection in Hyperspectral Images for Transfer Learning / Persello, Claudio; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 0196-2892. - 54:5(2016), pp. 2615-2626. [10.1109/TGRS.2015.2503885]

Kernel-Based Domain-Invariant Feature Selection in Hyperspectral Images for Transfer Learning

Bruzzone, Lorenzo
2016-01-01

Abstract

This paper presents a kernel-based feature selection method for the classification of hyperspectral images. The proposed method aims at selecting a subset of the original features that are both 1) relevant (discriminant) for the considered classification problem, i.e., preserve the functional relationship between input and output variables, and 2) invariant (stable) across different domains, i.e., minimize the data-set shift between the source and the target domains. Domains can be associated with hyperspectral images collected either on different geographical areas or on the same area at different times. We propose a novel measure of data-set shift for evaluating the domain stability, which computes the distance of the conditional distributions between the source and target domains in a reproducing kernel Hilbert space. Such a measure is defined on the basis of the kernel embeddings of the conditional distributions resulting in a nonparametric approach that does not require estimating the distribution of the classes. The adopted search strategy is based on a multiobjective optimization algorithm, which optimizes the two terms of the criterion function for the estimation of the Pareto-optimal solutions. This results in an effective approach of performing feature selection in a transfer learning setting. The experimental results obtained on two hyperspectral images show the effectiveness of the proposed method in selecting features with high generalization capabilities.
2016
5
Persello, Claudio; Bruzzone, Lorenzo
Kernel-Based Domain-Invariant Feature Selection in Hyperspectral Images for Transfer Learning / Persello, Claudio; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 0196-2892. - 54:5(2016), pp. 2615-2626. [10.1109/TGRS.2015.2503885]
File in questo prodotto:
File Dimensione Formato  
7.07360172.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.57 MB
Formato Adobe PDF
2.57 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/11572/168542
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 102
  • ???jsp.display-item.citation.isi??? 96
social impact