Can I read Adaptive Spectral-spatial Feature Fusion Network for Hyperspectral Image Classification Using Limited Training Samples on EtoBox?

Adaptive Spectral-spatial Feature Fusion Network for Hyperspectral Image Classification Using Limited Training Samples by Hongmin Gao; Zhonghao Chen; Feng Xu is a Environmental Science article available to read on EtoBox.

What is Adaptive Spectral-spatial Feature Fusion Network for Hyperspectral Image Classification Using Limited Training Samples about?

Recently, the excellent power of spectral-spatial feature representation of convolutional neural network (CNN) has gained widespread attention for hyperspectral image (HSI) classification. Nevertheless, the practical performance of CNN-based models in HSI classification is ordinarily limited by the available amount of the training samples. In this article, we investigate the limitations of current CNN-based methods for HSI feature (spectral and spatial) extraction and utilization. For spectral features, the distant inter-band relationships are often neglected. Therefore, a novel spectral band non-localization (SBNL) operation is proposed to enable the non-local spectral inter-band correlations to be excavated by convolutional kernels with limited receptive fields. For spatial features, the extracted spatial multiscale features conventionally isolated in different channels. Subsequently, we develop a novel multiscale-share inception block (MSIB) to exploit the cross-relationships among the multiscale features. More significantly, to better take advantage of the complementary information of spectral and spatial features, a plug-and-play adaptive feature fusion (AFF) module is introdu

Who reads Adaptive Spectral-spatial Feature Fusion Network for Hyperspectral Image Classification Using Limited Training Samples?

Author

Hongmin Gao; Zhonghao Chen; Feng Xu

Publisher

Elsevier BV

Published

2022

Language

EN

Field

Environmental Science (Physical Sciences)