Partial optimal transport-based domain adaptation for hyperspectral image classification

WANG Bilin; WANG Shengsheng; ZHANG Zhe

doi:10.37188/OPE.20233117.2555

您当前的位置：

首页 >

文章列表页 >

Partial optimal transport-based domain adaptation for hyperspectral image classification

Information Sciences | 更新时间：2023-09-22

- Partial optimal transport-based domain adaptation for hyperspectral image classification
- Optics and Precision Engineering Vol. 31, Issue 17, Pages: 2555-2563(2023)
- 作者机构：
  
  1.吉林大学计算机科学与技术学院，吉林长春 130012
  2.中国科学院苏州生物医学工程技术研究所，江苏苏州 215163
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20233117.2555
  CLC：
扫描看全文
WANG Bilin, WANG Shengsheng, ZHANG Zhe. Partial optimal transport-based domain adaptation for hyperspectral image classification. [J]. Optics and Precision Engineering 31(17):2555-2563(2023)
DOI：

WANG Bilin, WANG Shengsheng, ZHANG Zhe. Partial optimal transport-based domain adaptation for hyperspectral image classification. [J]. Optics and Precision Engineering 31(17):2555-2563(2023) DOI： 10.37188/OPE.20233117.2555.

摘要

针对高光谱遥感图像分类时有标注的源域训练数据与无标注目标域数据分布不一致的问题，提出基于部分最优传输的无监督领域自适应方法，实现对处于不同数据分布的高光谱遥感地物像素级分类。利用深度卷积神经网络将样本映射到潜在高维空间，根据部分最优传输理论建立样本传输方案，最小化域间分布差异，构建适配模型。采用类感知采样技术和质量分数因子自适应调整策略，促进域间类别对齐，建立全局最优传输。在两组公开高光谱遥感图像数据集上进行实验，从总体分类精度OA（%）、类别平均分类精度AA（%）、分类一致性检验Kappa（×100）等3个评价指标对像素分类结果量化比较。实验结果显示，在两组迁移任务上，相较于仅使用源域数据的基线模型，总体分类准确率分别提升2.21%和2.75%，相较于原始最优传输策略提升1.71%和2.01%，表明模型能够有效提升高光谱遥感影像中像素级地物的分类精度。

Abstract

Hyperspectral image classification is a major task in remote sensing data processing. To solve the problem of inconsistent distribution of labeled source and unlabeled target domains， an unsupervised domain adaptive method based on partial optimal transport is proposed to achieve pixel-level classification of hyperspectral ground objects under different data distributions. Specifically， a deep convolution neural network is used to map the sample to the potential high-dimensional space， and the sample transportation scheme is established based on the partial optimal transport theory to minimize the distribution discrepancy between domains. Class-aware sampling and the mass factor adaptive adjustment strategy are used to promote the class alignment between domains and establish a global optimal transport. Experiments were conducted on two open-source hyperspectral image datasets， and the classification accuracies were compared quantitatively from the three evaluation matrices of overall accuracy （OA， %）， average accuracy （AA， %）， and Kappa （×100）. Compared with the source-only method， the improved classification accuracies with the proposed method for OA and AA were 2.21% and 2.75%， respectively， and compared with the original optimal transport， the improved accuracies were 1.71% and 2.01%， respectively. These results show that the proposed model can effectively improve pixel-level classification accuracy in hyperspectral images.

关键词

计算机视觉神经网络领域自适应最优传输高光谱图像

Keywords

computer visionneural networkdomain adaptationoptimal transporthyperspectral image

references

杨坚华，张浩，花海洋. 并行路径与强注意力机制遥感图像建筑物分割［J］. 光学精密工程， 2023， 31（2）： 234-245. doi: 10.37188/ope.20233102.0234http://dx.doi.org/10.37188/ope.20233102.0234

YANG J H， ZHANG H， HUA H Y. Parallel path and strong attention mechanism for building segmentation in remote sensing images［J］. Opt. Precision Eng.， 2023， 31（2）： 234-245.（in Chinese）. doi: 10.37188/ope.20233102.0234http://dx.doi.org/10.37188/ope.20233102.0234

贾建鑫，孙海彬，蒋长辉，等. 多源遥感数据的道路提取技术研究现状及展望［J］. 光学精密工程， 2021， 29（2）： 430-442. doi: 10.37188/OPE.20212902.0430http://dx.doi.org/10.37188/OPE.20212902.0430

JIA J X， SUN H B， JIANG CH H， et al. Road extraction technology based on multi-source remote sensing：［J］. Opt. Precision Eng.， 2021， 29（2）： 430-442.（in Chinese）. doi: 10.37188/OPE.20212902.0430http://dx.doi.org/10.37188/OPE.20212902.0430

成丽波，李昂臻，贾小宁，等. 小波多重分形遥感图像混合去噪［J］. 光学精密工程， 2022， 30（15）： 1880-1888. doi: 10.37188/ope.20223015.1880http://dx.doi.org/10.37188/ope.20223015.1880

CHENG L B， LI A ZH， JIA X N， et al. Removing mixed noise from remote sensing images by wavelet multifractal method［J］. Opt. Precision Eng.， 2022， 30（15）： 1880-1888.（in Chinese）. doi: 10.37188/ope.20223015.1880http://dx.doi.org/10.37188/ope.20223015.1880

熊林. 无监督领域自适应目标检测方法研究［D］. 成都：电子科技大学， 2022.

XIONG L. Research on Unsupervised Adaptive Target Detection Method［D］. Chengdu： University of Electronic Science and Technology of China， 2022. （in Chinese）

LIU Z X， MA L， DU Q. Class-wise distribution adaptation for unsupervised classification of hyperspectral remote sensing images［J］. IEEE Transactions on Geoscience and Remote Sensing， 2021， 59（1）： 508-521. doi: 10.1109/tgrs.2020.2997863http://dx.doi.org/10.1109/tgrs.2020.2997863

MIAO J J， ZHANG B， WANG B. Coarse-to-fine joint distribution alignment for cross-domain hyperspectral image classification［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2021， 14： 12415-12428. doi: 10.1109/jstars.2021.3129177http://dx.doi.org/10.1109/jstars.2021.3129177

FANG Z Q， YANG Y X， LI Z K， et al. Confident learning-based domain adaptation for hyperspectral image classification［J］. IEEE Transactions on Geoscience and Remote Sensing， 2022， 60： 1-16. doi: 10.1109/tgrs.2022.3166817http://dx.doi.org/10.1109/tgrs.2022.3166817

LIANG X J， ZHANG Y， ZHANG J P. Attention multisource fusion-based deep few-shot learning for hyperspectral image classification［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2021， 14： 8773-8788. doi: 10.1109/jstars.2021.3109012http://dx.doi.org/10.1109/jstars.2021.3109012

MAKKAR N， YANG L X， PRASAD S. Adversarial learning based discriminative domain adaptation for geospatial image analysis［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2021， 15： 150-162. doi: 10.1109/jstars.2021.3132259http://dx.doi.org/10.1109/jstars.2021.3132259

BEN-DAVID S， BLITZER J， CRAMMER K， et al. Analysis of representations for domain adaptation［C］. Proceedings of the 19th International Conference on Neural Information Processing Systems. 47，2006， Canada. New York： ACM， 2006： 137-144. doi: 10.7551/mitpress/7503.003.0022http://dx.doi.org/10.7551/mitpress/7503.003.0022

VILLANI C. Optimal Transport： Old and New［M］. Berlin： Springer， 2009. doi: 10.1007/978-3-540-71050-9_28http://dx.doi.org/10.1007/978-3-540-71050-9_28

PEYRÉ G， CUTURI M. Computational optimal transport： with applications to data science［J］. Foundations and Trends® in Machine Learning， 2019， 11（5/6）： 355-607. doi: 10.1561/2200000073http://dx.doi.org/10.1561/2200000073

NGUYEN K， NGUYEN D， VU-LE T A， et al. Improving mini-batch optimal transport via partial transportation［EB/OL］. 2021： arXiv： 2108.09645. https：//arxiv.org/abs/2108.09645https://arxiv.org/abs/2108.09645. doi: 10.1109/mapr56351.2022.9924768http://dx.doi.org/10.1109/mapr56351.2022.9924768

ZHANG Y， LIU T， LONG M， et al. Bridging theory and algorithm for domain adaptation［EB/OL］. 2019： arXiv： 1904.05801. https：//arxiv.org/abs/1904.05801https://arxiv.org/abs/1904.05801.

LICCIARDI G， PACIFICI F， TUIA D， et al. Decision fusion for the classification of hyperspectral data： outcome of the 2008 GRS-S data fusion contest［J］. IEEE Transactions on Geoscience and Remote Sensing， 2009， 47（11）： 3857-3865. doi: 10.1109/tgrs.2009.2029340http://dx.doi.org/10.1109/tgrs.2009.2029340

2018 IEEE GRSS Data Fusion Contest ［OL］. Available： http：//www. grss-ieee.org/community/technical-committees/data-fusion/http://www.grss-ieee.org/community/technical-committees/data-fusion/. doi: 10.1109/mgrs.2014.2303201http://dx.doi.org/10.1109/mgrs.2014.2303201

JOACHIMS T. Transductive inference for text classification using support vector machines［C］. International Conference on Machine Learning.2730，1999， Bled， Slovenia. 1999， 99： 200-209.

LONG M S， CAO Y， WANG J M， et al. Learning transferable features with deep adaptation networks［C］. Proceedings of the 32nd International Conference on International Conference on Machine Learning-Volume 37.611，2015， Lille， France. New York： ACM， 2015： 97-105.

GANIN Y， USTINOVA E， AJAKAN H， et al. Domain-adversarial training of neural networks［J］. Advances in Computer Vision and Pattern Recognition， 2017（9783319583464）： 189-209. doi: 10.1007/978-3-319-58347-1_10http://dx.doi.org/10.1007/978-3-319-58347-1_10

DENG B， JIA S， SHI D M. Deep metric learning-based feature embedding for hyperspectral image classification［J］. IEEE Transactions on Geoscience and Remote Sensing， 2020， 58（2）： 1422-1435. doi: 10.1109/tgrs.2019.2946318http://dx.doi.org/10.1109/tgrs.2019.2946318

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Adaptive octree 3D image reconstruction based on plane patch

Multi-scale vehicle and pedestrian detection algorithm based on attention mechanism

Uniform defocus blind deblurring based on deeper feature-based wiener deconvolution

Multi-stage frame alignment video super- resolution network

Simulating primary visual cortex to improve robustness of CNN neural network structures

Related Author

No data

Related Institution

Xi'an Institute of Optics and Precision Mechanics， Chinese Academy of Sciences

University of Chinese Academy of Sciences

Institute of Intelligent Machines， Chinese Academy of Sciences

University of Science and Technology of China

Anhui Engineering Laboratory for Intelligent Driving Technology and Application

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰