Asymmetric Adaptation of Deep Features for Cross-Domain Classification in Remote Sensing Imagery

In this letter, we introduce an asymmetric adaptation neural network (AANN) method for cross-domain classification in remote sensing images. Before the adaptation process, we feed the features obtained from a pretrained convolutional neural network to a denoising autoencoder (DAE) to perform dimensi...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE geoscience and remote sensing letters Ročník 15; číslo 4; s. 597 - 601
Hlavní autori: Ammour, Nassim, Bashmal, Laila, Bazi, Yakoub, Al Rahhal, M. M., Zuair, Mansour
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 01.04.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Adaptation
Artificial neural networks
Asymmetric adaptation neural network (AANN)
Classification
cross-domain classification
Data
Datasets
deep features
Detection
Feature extraction
Feeds
Image classification
Imagery
Land cover
Linear programming
Neural networks
Niobium
Noise reduction
Objective function
Remote sensing
Separation
Training
ISSN:1545-598X, 1558-0571
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this letter, we introduce an asymmetric adaptation neural network (AANN) method for cross-domain classification in remote sensing images. Before the adaptation process, we feed the features obtained from a pretrained convolutional neural network to a denoising autoencoder (DAE) to perform dimensionality reduction. Then the first hidden layer of AANN (placed on the top of DAE) maps the labeled source data to the target space, while the subsequent layers control the separation between the available land-cover classes. To learn its weights, the network minimizes an objective function composed of two losses related to the distance between the source and target data distributions and class separation. The results of experiments conducted on six scenarios built from three benchmark scene remote sensing data sets (i.e., Merced, KSA, and AID data sets) are reported and discussed.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2018.2800642