Show simple item record

dc.contributor.authorLi, Ningyang
dc.contributor.authorWang, Zhaohui
dc.contributor.authorAlaya Cheikh, Faouzi
dc.contributor.authorUllah, Mohib
dc.date.accessioned2023-02-28T08:26:46Z
dc.date.available2023-02-28T08:26:46Z
dc.date.created2022-10-16T16:51:18Z
dc.date.issued2022
dc.identifier.citationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2022, 15 5984-5998.en_US
dc.identifier.issn1939-1404
dc.identifier.urihttps://hdl.handle.net/11250/3054503
dc.description.abstractRecently, hyperspectral image (HSI) classification based on deep learning methods has attracted growing attention and made great progress . Convolutional neural networks based models, especially the residual networks (ResNets), have become the architectures of choice for extracting the deep spectral-spatial features. However, there are generally some interfering pixels in the neighborhoods of the center pixel, which are unfavorable for the spectral-spatial feature extraction and will lead to a restraint classification performance. More important, the existing attention modules are weak in highlighting the effect of the center pixel for the spatial attention. To solve this issue, this article proposes a novel spectral-similarity-based spatial attention module (S 3 AM) to emphasize the relevant spatial areas in HSI. The S 3 AM adopts the weighted Euclidean and cosine distances to measure the spectral similarities between the center pixel and its neighborhoods. To alleviate the negative influence of the spectral variability, the full-band convolutional layers are deployed to reweight the bands for the robust spectral similarities. Both kinds of weighted spectral similarities are then fused adaptively to take their relative importance into full account. Finally, a scalable Gaussian activation function, which can suppress the interfering pixels dynamically, is installed to transform the spectral similarities into the appropriate spatial weights. The S 3 AM is integrated with the ResNet to build the S 3 AM-Net model, which is able to extract the discriminating spectral-spatial features. Experimental results on four public HSI datasets demonstrate the effectiveness of the proposed attention module and the outstanding classification performance of the S 3 AM-Net model.en_US
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.rightsNavngivelse 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.no*
dc.titleS3AM: A Spectral-Similarity-Based Spatial Attention Module for Hyperspectral Image Classificationen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionpublishedVersionen_US
dc.source.pagenumber5984-5998en_US
dc.source.volume15en_US
dc.source.journalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensingen_US
dc.identifier.doi10.1109/JSTARS.2022.3191396
dc.identifier.cristin2061753
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Navngivelse 4.0 Internasjonal
Except where otherwise noted, this item's license is described as Navngivelse 4.0 Internasjonal