Hyperspectral images (HSIs) provide rich spectral-spatial information with stacked hundreds of contiguous narrowbands. Due to the existence of noise and band correlation, the selection of informative spectral-spatial kernel features poses a challenge. This is often addressed by using convolutional neural networks (CNNs) with receptive field (RF) having fixed sizes. However, these solutions cannot enable neurons to effectively adjust RF sizes and cross-channel dependencies when forward and backward propagations are used to optimize the network. In this article, we present an attention-based adaptive spectral-spatial kernel improved residual network (A(2)S(2)K-ResNet) with spectral attention to capture discriminative spectral-spatial features for HSI classification in an end-to-end training fashion. In particular, the proposed network learns selective 3-D convolutional kernels to jointly extract spectral-spatial features using improved 3-D ResBlocks and adopts an efficient feature recalibration (EFR) mechanism to boost the classification performance. Extensive experiments are performed on three well-known hyperspectral data sets, i.e., IP, KSC, and UP, and the proposed A(2)S(2)K-ResNet can provide better classification results in terms of overall accuracy (OA), average accuracy (AA), and Kappa compared with the existing methods investigated. The source code will be made available at https://github.com/suvojit-0 x 55aa/A2S2K-ResNet.

Attention-Based Adaptive Spectral–Spatial Kernel ResNet for Hyperspectral Image Classification / Kumar Roy, Swalpa; Manna, Suvojit; Song, Tiecheng; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 0196-2892. - 59:9(2021), pp. 7831-7843. [10.1109/tgrs.2020.3043267]

Attention-Based Adaptive Spectral–Spatial Kernel ResNet for Hyperspectral Image Classification

Bruzzone, Lorenzo
2021-01-01

Abstract

Hyperspectral images (HSIs) provide rich spectral-spatial information with stacked hundreds of contiguous narrowbands. Due to the existence of noise and band correlation, the selection of informative spectral-spatial kernel features poses a challenge. This is often addressed by using convolutional neural networks (CNNs) with receptive field (RF) having fixed sizes. However, these solutions cannot enable neurons to effectively adjust RF sizes and cross-channel dependencies when forward and backward propagations are used to optimize the network. In this article, we present an attention-based adaptive spectral-spatial kernel improved residual network (A(2)S(2)K-ResNet) with spectral attention to capture discriminative spectral-spatial features for HSI classification in an end-to-end training fashion. In particular, the proposed network learns selective 3-D convolutional kernels to jointly extract spectral-spatial features using improved 3-D ResBlocks and adopts an efficient feature recalibration (EFR) mechanism to boost the classification performance. Extensive experiments are performed on three well-known hyperspectral data sets, i.e., IP, KSC, and UP, and the proposed A(2)S(2)K-ResNet can provide better classification results in terms of overall accuracy (OA), average accuracy (AA), and Kappa compared with the existing methods investigated. The source code will be made available at https://github.com/suvojit-0 x 55aa/A2S2K-ResNet.
2021
9
Kumar Roy, Swalpa; Manna, Suvojit; Song, Tiecheng; Bruzzone, Lorenzo
Attention-Based Adaptive Spectral–Spatial Kernel ResNet for Hyperspectral Image Classification / Kumar Roy, Swalpa; Manna, Suvojit; Song, Tiecheng; Bruzzone, Lorenzo. - In: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING. - ISSN 0196-2892. - 59:9(2021), pp. 7831-7843. [10.1109/tgrs.2020.3043267]
File in questo prodotto:
File Dimensione Formato  
Attention-Based_Adaptive_SpectralSpatial_Kernel_ResNet_for_Hyperspectral_Image_Classification.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 6.03 MB
Formato Adobe PDF
6.03 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/11572/401505
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 224
  • ???jsp.display-item.citation.isi??? 213
social impact