Tensor-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification

Few-shot learning (FSL) is an effective solution for cross-domain hyperspectral image (HSI) classification, which could address the limited labeled samples of the target domain. Current FSL methods mostly utilize the 3D-CNN to transform the spatial and spectral information into a single feature to m...

Full description

Saved in:
Bibliographic Details
Main Authors: Haojin Tang, Xiaofei Yang, Dong Tang, Yiru Dong, Li Zhang, Weixin Xie
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/22/4149
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152589551337472
author Haojin Tang
Xiaofei Yang
Dong Tang
Yiru Dong
Li Zhang
Weixin Xie
author_facet Haojin Tang
Xiaofei Yang
Dong Tang
Yiru Dong
Li Zhang
Weixin Xie
author_sort Haojin Tang
collection DOAJ
description Few-shot learning (FSL) is an effective solution for cross-domain hyperspectral image (HSI) classification, which could address the limited labeled samples of the target domain. Current FSL methods mostly utilize the 3D-CNN to transform the spatial and spectral information into a single feature to model an HSI, which means that spatial and spectral information are treated equally in the feature-modeling process. However, spectral information is considered to be more domain-invariant than spatial information. Treating the spatial and spectral information equally may result in parameter redundancy and undesirable cross-domain classification performance. In this paper, we attempt to use tensor mathematics for modeling the HSI and propose a novel few-shot learning method, called tensor-based few-shot Learning (TFSL) for cross-domain HSI classification, which aims to guide the model to focus on the extraction of domain-invariant spectral dependencies. Specifically, we first propose a spatial–spectral tensor decomposition (SSTD) model to provide a mathematical explanation of the input HSI, representing the local spatial–spectral information as 1D and 2D local tensors to reduce the data redundancy. Additionally, a tensor-based hybrid two-stream (THT) model is proposed for extracting the domain-invariant spatial–spectral tensor feature by using 1D-CNN and 2D-CNN. Furthermore, we adopt a 1D-CNN tensor feature enhancement block to enhance the spectral feature of hybrid two-stream tensors and guide the THT model to concentrate on the modeling of spectral dependencies. Finally, the proposed TFSL is evaluated on four public HSI datasets, and the extensive experimental results demonstrate that the proposed TFSL significantly outperforms other advanced FSL methods.
format Article
id doaj-art-9d25dff679534d3ba99c22853f90c438
institution Kabale University
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-9d25dff679534d3ba99c22853f90c4382024-11-26T18:19:43ZengMDPI AGRemote Sensing2072-42922024-11-011622414910.3390/rs16224149Tensor-Based Few-Shot Learning for Cross-Domain Hyperspectral Image ClassificationHaojin Tang0Xiaofei Yang1Dong Tang2Yiru Dong3Li Zhang4Weixin Xie5School of Electronic and Communication Engineering, Guangzhou University, Guangzhou 511370, ChinaSchool of Electronic and Communication Engineering, Guangzhou University, Guangzhou 511370, ChinaSchool of Electronic and Communication Engineering, Guangzhou University, Guangzhou 511370, ChinaSchool of Electronic and Communication Engineering, Guangzhou University, Guangzhou 511370, ChinaGuangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, ChinaGuangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, ChinaFew-shot learning (FSL) is an effective solution for cross-domain hyperspectral image (HSI) classification, which could address the limited labeled samples of the target domain. Current FSL methods mostly utilize the 3D-CNN to transform the spatial and spectral information into a single feature to model an HSI, which means that spatial and spectral information are treated equally in the feature-modeling process. However, spectral information is considered to be more domain-invariant than spatial information. Treating the spatial and spectral information equally may result in parameter redundancy and undesirable cross-domain classification performance. In this paper, we attempt to use tensor mathematics for modeling the HSI and propose a novel few-shot learning method, called tensor-based few-shot Learning (TFSL) for cross-domain HSI classification, which aims to guide the model to focus on the extraction of domain-invariant spectral dependencies. Specifically, we first propose a spatial–spectral tensor decomposition (SSTD) model to provide a mathematical explanation of the input HSI, representing the local spatial–spectral information as 1D and 2D local tensors to reduce the data redundancy. Additionally, a tensor-based hybrid two-stream (THT) model is proposed for extracting the domain-invariant spatial–spectral tensor feature by using 1D-CNN and 2D-CNN. Furthermore, we adopt a 1D-CNN tensor feature enhancement block to enhance the spectral feature of hybrid two-stream tensors and guide the THT model to concentrate on the modeling of spectral dependencies. Finally, the proposed TFSL is evaluated on four public HSI datasets, and the extensive experimental results demonstrate that the proposed TFSL significantly outperforms other advanced FSL methods.https://www.mdpi.com/2072-4292/16/22/4149few-shot learningcross-domain hyperspectral image classificationtensor mathematics
spellingShingle Haojin Tang
Xiaofei Yang
Dong Tang
Yiru Dong
Li Zhang
Weixin Xie
Tensor-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification
Remote Sensing
few-shot learning
cross-domain hyperspectral image classification
tensor mathematics
title Tensor-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification
title_full Tensor-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification
title_fullStr Tensor-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification
title_full_unstemmed Tensor-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification
title_short Tensor-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification
title_sort tensor based few shot learning for cross domain hyperspectral image classification
topic few-shot learning
cross-domain hyperspectral image classification
tensor mathematics
url https://www.mdpi.com/2072-4292/16/22/4149
work_keys_str_mv AT haojintang tensorbasedfewshotlearningforcrossdomainhyperspectralimageclassification
AT xiaofeiyang tensorbasedfewshotlearningforcrossdomainhyperspectralimageclassification
AT dongtang tensorbasedfewshotlearningforcrossdomainhyperspectralimageclassification
AT yirudong tensorbasedfewshotlearningforcrossdomainhyperspectralimageclassification
AT lizhang tensorbasedfewshotlearningforcrossdomainhyperspectralimageclassification
AT weixinxie tensorbasedfewshotlearningforcrossdomainhyperspectralimageclassification