基于局部表征少样本学习的高光谱图像跨场景分类

张宇翔; 李伟; 张蒙蒙; 陶然

doi:10.12263/DZXB.20230937

您当前的位置：

首页 >

文章列表页 >

基于局部表征少样本学习的高光谱图像跨场景分类

学术论文 | 更新时间：2025-12-08

- 基于局部表征少样本学习的高光谱图像跨场景分类
- Local Representation Few-Shot Learning for Hyperspectral Image Cross-Scene Classification
- 电子学报 2025年53卷第1期页码：248-258
- 作者机构：
  
  北京理工大学信息与电子学院，北京 100081
- 作者简介：
  
  [ "张宇翔男，1995年1月出生于青海省西宁市.北京理工大学信息与电子学院博士研究生.主要研究方向为高光谱图像跨域分类.中国电子学会会员编号：E190159510M." ]
  [ "李伟，男，1985年2月出生于湖北省随州市.现为北京理工大学信息与电子学院教授.主要研究方向为高光谱图像处理 E-mail: liw@bit.edu.cn" ]
  [ "张蒙蒙，女，1994年6月出生于山东省济宁市.现为北京理工大学信息与电子学院副研究员.主要研究方向为高光谱图像处理. E-mail: mengmengzhang@bit.edu.cn" ]
- 基金信息：
  
  多光谱信息智能处理技术全国重点实验室资助项目(6142113220205);北京理工大学研究生科研水平和创新能力提升专项计划(2023YCXZ008)
- DOI：10.12263/DZXB.20230937
  中图分类号： TP75;TP79
- 收稿：2023-10-07，
  
  修回：2024-01-19，
  
  纸质出版：2025-01-25
- 稿件说明：
移动端阅览
张宇翔, 李伟, 张蒙蒙, 等. 基于局部表征少样本学习的高光谱图像跨场景分类[J]. 电子学报, 2025, 53(01): 248-258.

ZHANG Yu-xiang, LI Wei, ZHANG Meng-meng, et al. Local Representation Few-Shot Learning for Hyperspectral Image Cross-Scene Classification[J]. Acta Electronica Sinica, 2025, 53(01): 248-258.
张宇翔, 李伟, 张蒙蒙, 等. 基于局部表征少样本学习的高光谱图像跨场景分类[J]. 电子学报, 2025, 53(01): 248-258. DOI：10.12263/DZXB.20230937

ZHANG Yu-xiang, LI Wei, ZHANG Meng-meng, et al. Local Representation Few-Shot Learning for Hyperspectral Image Cross-Scene Classification[J]. Acta Electronica Sinica, 2025, 53(01): 248-258. DOI：10.12263/DZXB.20230937

摘要

在跨场景分类任务中，大多数领域自适应方法（Domain Adaptation，DA）关注于源域数据和目标域数据由相同传感器获得且具有相同地物类别的迁移任务，然而当目标数据中存在新类别时自适应性能会显著下降.此外，大多数高光谱图像分类方法采用全局表征机制，即针对固定大小窗口的样本进行表征学习，其地物类别表征能力有限.本文提出了一种基于局部表征的少样本学习框架（Local representation Few Shot Learning，LrFSL），尝试在少样本学习中构建局部表征机制突破全局表征能力上限.在提出框架中，对所有具有标签的源域数据和少量具有标签的目标域数据构建元任务，依照元学习策略同步进行情景训练，与此同时设计了域内局部表征模块（Intra-domain Local Representation block，ILR-block）用于挖掘样本中多个局部表征的语义信息，设计了域间局部对齐模块（Inter-domain Local Alignment block，ILA-block）进行跨域逐类别分布对齐以缓解领域偏移对少样本学习的影响.在三个公开高光谱图像数据集上的实验结果证明了该方法显著优于目前最先进的方法.

Abstract

In cross-scene classification tasks

most domain adaptation (DA) methods typically focus on transfer tasks where the source domain data and the target domain data are obtained using the same sensor and share the same land cover class. However

the adaptive performance is significantly reduced when new classes are present in the target data. Moreover

many hyperspectral image (HSI) classification methods rely on a global representation mechanism

where representation learning is performed on samples with fixed-size windows

limiting their ability to effectively represent ground object classes. A framework called local representation few-shot learning (LrFSL) is proposed

which aims to overcome the limitations of global representation ability by constructing a local representation mechanism in few-shot learning. In this proposed framework

meta-tasks are created for all labeled source domain data and a few labeled target domain data

and scenario training is performed simultaneously using a meta-learning strategy. Additionally

an Intra-domain local representation block (ILR-block) is designed to extract semantic information from multiple local representations within each sample. Furthermore

the inter-domain local alignment block (ILA-block) is designed to align cross-domain class-wise distribution

thereby mitigating the impact of domain shift on few-shot learning. Experimental results on three publicly available HSI datasets demonstrate that the proposed method outperforms state-of-the-art methods by a significant margin.

关键词

Keywords

references

TUIA D , PERSELLO C , BRUZZONE L . Domain adaptation for the classification of remote sensing data: An overview of recent advances [J ] . IEEE Geoscience and Remote Sensing Magazine , 2016 , 4 ( 2 ): 41 - 57 .

ELSHAMLI A , TAYLOR G W , BERG A , et al . Domain adaptation using representation learning for the classification of remote sensing images [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2017 , 10 ( 9 ): 4198 - 4209 .

ZHANG J , LIU J , PAN B , et al . Domain adaptation based on correlation subspace dynamic distribution alignment for remote sensing image scene classification [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2020 , 58 ( 11 ): 7920 - 7930 .

YANG J F , CHEN H L , XU Y C , et al . Domain adaptation for degraded remote scene classification [C ] // 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV) . Piscataway : IEEE , 2020 : 111 - 117 .

KWAK G H , PARK N W . Unsupervised domain adaptation with adversarial self-training for crop classification using remote sensing images [J ] . Remote Sensing , 2022 , 14 ( 18 ): 4639 .

WANG J J , MA A L , ZHONG Y F , et al . Cross-sensor domain adaptation for high spatial resolution urban land-cover mapping: From airborne to spaceborne imagery [J ] . Remote Sensing of Environment , 2022 , 277 : 113058 .

QU Y , BAGHBADERANI R K , LI W , et al . Physically constrained transfer learning through shared abundance space for hyperspectral image classification [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2021 , 59 ( 12 ): 10455 - 10472 .

ZHU Y C , ZHUANG F Z , WANG J D , et al . Deep subdomain adaptation network for image classification [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2021 , 32 ( 4 ): 1713 - 1722 .

LIU T Z , ZHANG X R , GU Y F . Unsupervised cross-temporal classification of hyperspectral images with multiple geodesic flow kernel learning [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 12 ): 9688 - 9701 .

LUO C , MA L . Manifold regularized distribution adaptation for classification of remote sensing images [J ] . IEEE Access , 2018 , 6 : 4697 - 4708 .

SUN H , LIU S , ZHOU S L , et al . Unsupervised cross-view semantic transfer for remote sensing image classification [J ] . IEEE Geoscience and Remote Sensing Letters , 2016 , 13 ( 1 ): 13 - 17 .

HUANG Y , PENG J T , CHEN N , et al . Cross-scene wetland mapping on hyperspectral remote sensing images using adversarial domain adaptation network [J ] . ISPRS Journal of Photogrammetry and Remote Sensing , 2023 , 203 : 37 - 54 .

SUN Q R , LIU Y Y , CHUA T S , et al . Meta-transfer learning for few-shot learning [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2019 : 403 - 412 .

HOU R B , CHANG H , MA B P , et al . Cross attention network for few-shot classification [C ] // Proceedings of the 33rd International Conference on Neural Information Processing Systems . New York : ACM , 2019 : 4003 - 4024 .

SUNG F , YANG Y X , ZHANG L , et al . Learning to compare: Relation network for few-shot learning [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 1199 - 1208 .

SNELL J , SWERSKY K , ZEMEL R , et al . Prototypical networks for few-shot learning [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . New York : ACM , 2017 : 4080 - 4090 .

SUN X , WANG B , WANG Z R , et al . Research progress on few-shot learning for remote sensing image interpretation [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2021 , 14 : 2387 - 2402 .

HUANG H W , WU Z K , LI W B , et al . Local descriptor-based multi-prototype network for few-shot learning [J ] . Pattern Recognition , 2021 , 116 : 107935 .

ZHANG C Y , YUE J , QIN Q M . Global prototypical network for few-shot hyperspectral image classification [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2020 , 13 : 4748 - 4759 .

LIU S J , SHI Q , ZHANG L P . Few-shot hyperspectral image classification with unknown classes using multitask deep learning [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2021 , 59 ( 6 ): 5085 - 5102 .

ZHANG Y X , LI W , ZHANG M M , et al . Graph information aggregation cross-domain few-shot learning for hyperspectral image classification [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2024 , 35 ( 2 ): 1912 - 1925 .

LIU B , YU X C , YU A Z , et al . Deep few-shot learning for hyperspectral image classification [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 4 ): 2290 - 2304 .

GAO K L , LIU B , YU X C , et al . Deep relation network for hyperspectral image few-shot classification [J ] . Remote Sensing , 2020 , 12 ( 6 ): 923 .

ZHANG M M , ZHAO X D , LI W , et al . Cross-scene joint classification of multisource data with multilevel domain adaption network [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2024 , 35 ( 8 ): 11514 - 11526 .

万升 , 杨健 , 宫辰 . 基于图神经网络的高光谱图像分类研究进展 [J ] . 电子学报 , 2023 , 51 ( 6 ): 1687 - 1709 .

WAN S , YANG J , GONG C . Advances of hyperspectral image classification based on graph neural networks [J ] . Acta Electronica Sinica , 2023 , 51 ( 6 ): 1687 - 1709 . (in Chinese)

ZHANG Y X , LI W , TAO R , et al . Cross-scene hyperspectral image classification with discriminative cooperative alignment [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2021 , 59 ( 11 ): 9646 - 9660 .

YU C H , WANG J D , CHEN Y Q , et al . Transfer learning with dynamic adversarial adaptation network [C ] // 2019 IEEE International Conference on Data Mining (ICDM) . Piscataway : IEEE , 2019 : 778 - 786 .

YANG L , LI L L , ZHANG Z L , et al . DPGN: Distribution propagation graph network for few-shot learning [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 13387 - 13396 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于元学习的图卷积网络少样本学习模型

基于多层小波深度聚合网络的高光谱图像超分辨率方法

高光谱图像分数域信息提取理论与方法进展

一种基于混合整型变换和3D-SPIHT的高光谱图像嵌入式无损压缩方法

加密流量侧信道泄漏的不可避免性