论文阅读笔记:多模态的融合数据和方法

论文题目: Multimodal remote sensing benchmark datasets for land cover classification with a shared and specific feature learning model
论文链接: https://www.sciencedirect.com/science/article/pii/S0924271621001362?dgcid=rss_sd_all.
代码链接:https://github.com/danfenghong/ISPRS_S2FL
引用方式:

@article{HONG202168,
title = {Multimodal remote sensing benchmark datasets for land cover classification with a shared and specific feature learning model},
journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
volume = {178},
pages = {68-80},
year = {2021},
issn = {0924-2716},
doi = {https://doi.org/10.1016/j.isprsjprs.2021.05.011},
url = {https://www.sciencedirect.com/science/article/pii/S0924271621001362},
author = {Danfeng Hong and Jingliang Hu and Jing Yao and Jocelyn Chanussot and Xiao Xiang Zhu},
}

一、背景:融合方法

① 特征级联

② 共有特征和特有特征的分离处理

二、本文的方法

本文使用第二种融合方法

三、数据

①:HS-MS Houston2013 data
论文阅读笔记:多模态的融合数据和方法_第1张图片
②:HS-SAR Berlin data
论文阅读笔记:多模态的融合数据和方法_第2张图片
③:HS-SAR-DSM augsburg data
论文阅读笔记:多模态的融合数据和方法_第3张图片
下载链接:https://pan.baidu.com/s/14OQW-9EpGRODOEnWfBXnag
提取码: ekqq

注:本文仅用来做学习笔记,如有侵权,请联系[email protected]

你可能感兴趣的:(计算机视觉,paper,学习笔记,人工智能)