Show simple item record

dc.contributor.author Zhang, Haokui
dc.contributor.author Li, Ying
dc.contributor.author Jiang, Yenan
dc.contributor.author Wang, Peng
dc.contributor.author Shen, Qiang
dc.contributor.author Shen, Chunhua
dc.date.accessioned 2020-02-23T01:32:29Z
dc.date.available 2020-02-23T01:32:29Z
dc.date.issued 2019-08-01
dc.identifier.citation Zhang , H , Li , Y , Jiang , Y , Wang , P , Shen , Q & Shen , C 2019 , ' Hyperspectral classification based on lightweight 3D-CNN with transfer learning. ' IEEE Transactions on Geoscience and Remote Sensing , vol. 57 , no. 8 , pp. 5813-5828 . https://doi.org/10.1109/TGRS.2019.2902568 en
dc.identifier.issn 0196-2892
dc.identifier.other PURE: 29354733
dc.identifier.other PURE UUID: 4efbf287-96ee-4cba-9791-1d50c0ab8217
dc.identifier.other Scopus: 85069753764
dc.identifier.other handle.net: http://hdl.handle.net/2160/4efbf287-96ee-4cba-9791-1d50c0ab8217
dc.identifier.uri http://hdl.handle.net/2160/47288
dc.description.abstract Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL) models have been proposed and shown promising performance. However, due to very limited available training samples and massive model parameters, deep learning methods may suffer from over-fitting. In this paper, we propose an end-to-end 3D lightweight convolutional neural network (CNN) (abbreviated as 3D-LWNet) for limited samples based HSI classification. Compared with conventional 3D-CNN models, the proposed 3D-LWNet has deeper network structure, less parameters and lower computation cost, while it results in better classification performance. To further alleviate the small sample problem, we also propose two transfer learning strategies: 1) cross-sensor strategy. We pretrain a 3D model in the source HSI datasets containing a greater number of labeled samples and then transfer it to the target HSI datasets; and 2) cross-modal strategy. We pretrain a 3D model in the 2D RGB image datasets containing a large number of samples and then transfer it to the target HSI datasets. In contrast to previous approaches, we do not impose restrictions over the source datasets in that they do not have to be collected by the same senors as the target datasets. Experiments on three public HSI datasets captured by different sensors demonstrate that our model achieves competitive performance for HSI classification compared to several state-of-the-art methods en
dc.format.extent 16 en
dc.language.iso eng
dc.relation.ispartof IEEE Transactions on Geoscience and Remote Sensing en
dc.rights en
dc.subject hyperspectral classification en
dc.subject deep learning en
dc.subject 3D lightweight convolutional network en
dc.subject transfer learning en
dc.title Hyperspectral classification based on lightweight 3D-CNN with transfer learning. en
dc.type /dk/atira/pure/researchoutput/researchoutputtypes/contributiontojournal/article en
dc.description.version authorsversion en
dc.identifier.doi https://doi.org/10.1109/TGRS.2019.2902568
dc.contributor.institution Faculty of Business and Physical Sciences en
dc.description.status Peer reviewed en


Files in this item

Aside from theses and in the absence of a specific licence document on an item page, all works in Cadair are accessible under the CC BY-NC-ND Licence. AU theses and dissertations held on Cadair are made available for the purposes of private study and non-commercial research and brief extracts may be reproduced under fair dealing for the purpose of criticism or review. If you have any queries in relation to the re-use of material on Cadair, contact is@aber.ac.uk.

This item appears in the following Collection(s)

Show simple item record

Search Cadair


Advanced Search

Browse

Statistics