Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model for Hyperspectral Image Classification

Deng, C; Xue, Y; Liu, X; Li, C; Tao, D

Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model for Hyperspectral Image Classification

Deng, C Xue, Y Liu, X Li, C Tao, D

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Geoscience and Remote Sensing, 2019, 57 (3), pp. 1741 - 1754
Issue Date:: 2019-03-01

Closed Access

	Filename	Description	Size
	08520902.pdf	Published Version	5.09 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Deng, C	en_US
dc.contributor.author	Xue, Y	en_US
dc.contributor.author	Liu, X	en_US
dc.contributor.author	Li, C	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.date.issued	2019-03-01	en_US
dc.identifier.citation	IEEE Transactions on Geoscience and Remote Sensing, 2019, 57 (3), pp. 1741 - 1754	en_US
dc.identifier.issn	0196-2892	en_US
dc.identifier.uri	http://hdl.handle.net/10453/137496
dc.description.abstract	© 2019 IEEE. Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network mostly relies on a large number of labeled samples being available. To address this problem, this paper proposes a unified deep network, combined with active transfer learning (TL) that can be well-trained for HSIs classification using only minimally labeled training data. More specifically, deep joint spectral-spatial feature is first extracted through hierarchical stacked sparse autoencoder (SSAE) networks. Active TL is then exploited to transfer the pretrained SSAE network and the limited training samples from the source domain to the target domain, where the SSAE network is subsequently fine-tuned using the limited labeled samples selected from both source and target domains by the corresponding active learning (AL) strategies. The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel AL strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross data set and intraimage; and 3) the learned deep joint spectral-spatial feature representation is more generic and robust than many joint spectral-spatial feature representations. Extensive comparative evaluations demonstrate that our proposed method significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based methods, on three popular data sets.	en_US
dc.relation.ispartof	IEEE Transactions on Geoscience and Remote Sensing	en_US
dc.relation.isbasedon	10.1109/TGRS.2018.2868851	en_US
dc.subject.classification	Geological & Geomatics Engineering	en_US
dc.title	Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model for Hyperspectral Image Classification	en_US
dc.type	Journal Article
utslib.citation.volume	3	en_US
utslib.citation.volume	57	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0102 Applied Mathematics	en_US
utslib.for	0404 Geophysics	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	0909 Geomatic Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.issue	3	en_US
pubs.publication-status	Published	en_US
pubs.volume	57	en_US

Abstract:

© 2019 IEEE. Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network mostly relies on a large number of labeled samples being available. To address this problem, this paper proposes a unified deep network, combined with active transfer learning (TL) that can be well-trained for HSIs classification using only minimally labeled training data. More specifically, deep joint spectral-spatial feature is first extracted through hierarchical stacked sparse autoencoder (SSAE) networks. Active TL is then exploited to transfer the pretrained SSAE network and the limited training samples from the source domain to the target domain, where the SSAE network is subsequently fine-tuned using the limited labeled samples selected from both source and target domains by the corresponding active learning (AL) strategies. The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel AL strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross data set and intraimage; and 3) the learned deep joint spectral-spatial feature representation is more generic and robust than many joint spectral-spatial feature representations. Extensive comparative evaluations demonstrate that our proposed method significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based methods, on three popular data sets.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/137496