Category-sensitive semi-supervised semantic segmentation framework for land-use/land-cover mapping with optical remote sensing images
文献类型：期刊论文
| 作者 | Chen, Jifa3,4,5; Chen, Gang3; Zhang, Li4,5; Huang, Min4,5; Luo, Jin4,5; Ding, Mingjun4,5; Ge, Yong2,4,5 |
| 刊名 | INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
 |
| 出版日期 | 2024-11-01 |
| 卷号 | 134页码:104160 |
| 关键词 | Land-use/land-cover mapping Semantic segmentation Semi-supervised learning Optical remote sensing images |
| DOI | 10.1016/j.jag.2024.104160 |
| 产权排序 | 5 |
| 文献子类 | Article |
| 英文摘要 | High-quality land-use/land-cover mapping with optical remote sensing images yet presents significant work. Even though fully convolutional semantic segmentation models have recently contributed to popular solutions, the lack of annotation data may lead to severe degradations in their inference performance. Besides, the category confusion in high-resolution representations will further exacerbate the adverse effects. In this paper, we propose a category-sensitive semi-supervised semantic segmentation framework to address these weaknesses by employing massive unlabeled data. With the perturbations from adopted hybrid data augmentation structures, we first focus on the output space and execute regularization constraints to learn category-specific discriminative features. It is formulated with a consistency self-training procedure where a dynamic class-balanced threshold selection scheme is proposed to provide high-confident pseudo supervisions for each category. In addition, we introduce pixel-wise contrastive learning on the common embedding space from both labeled and unlabeled data domains to further facilitate the semantic dependencies among category features, in which the reliable labels are leveraged as guidance for pixel sample selection. We verify the proposed framework on two benchmark land-use/ land-cover datasets, and the experimental results demonstrate its competitive performance to other state-of-theart semi-supervised methods. |
| WOS研究方向 | Remote Sensing |
| WOS记录号 | WOS:001316867400001 |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/207937]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Ge, Yong |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 2.China Univ Geosci, Coll Marine Sci & Technol, Wuhan 430074, Peoples R China 3.Jiangxi Normal Univ, Sch Geog & Environm, Nanchang 330022, Peoples R China 4.Key Lab Nat Disaster Monitoring Early Warning & As, Nanchang 330022, Peoples R China 5.Jiangxi Normal Univ, Key Lab Poyang Lake Wetland & Watershed Res, Minist Educ, Nanchang 330022, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chen, Jifa,Chen, Gang,Zhang, Li,et al. Category-sensitive semi-supervised semantic segmentation framework for land-use/land-cover mapping with optical remote sensing images[J]. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,2024,134:104160. |
| APA | Chen, Jifa.,Chen, Gang.,Zhang, Li.,Huang, Min.,Luo, Jin.,...&Ge, Yong.(2024).Category-sensitive semi-supervised semantic segmentation framework for land-use/land-cover mapping with optical remote sensing images.INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,134,104160. |
| MLA | Chen, Jifa,et al."Category-sensitive semi-supervised semantic segmentation framework for land-use/land-cover mapping with optical remote sensing images".INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 134(2024):104160. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。