Efficient greenhouse segmentation with visual foundation models: achieving more with fewer samples
文献类型：期刊论文
| 作者 | Lu, Yuxiang2,3; Wang, Jiahe2,3; Wang, Dan1; Liu, Tang2 |
| 刊名 | FRONTIERS IN ENVIRONMENTAL SCIENCE
 |
| 出版日期 | 2024-07-30 |
| 卷号 | 12页码:1395337 |
| 关键词 | visual foundation model remote sensing downstream tasks greenhouse deep Learning remote sensing foundation model |
| DOI | 10.3389/fenvs.2024.1395337 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Introduction: The Vision Transformer (ViT) model, which leverages self-supervised learning, has shown exceptional performance in natural image segmentation, suggesting its extensive potential in visual tasks. However, its effectiveness diminishes in remote sensing due to the varying perspectives of remote sensing images and unique optical properties of features like the translucency of greenhouses. Additionally, the high cost of training Visual Foundation Models (VFMs) from scratch for specific scenes limits their deployment.Methods: This study investigates the feasibility of rapidly deploying VFMs on new tasks by using embedding vectors generated by VFMs as prior knowledge to enhance traditional segmentation models' performance. We implemented this approach to improve the accuracy and robustness of segmentation with the same number of trainable parameters. Comparative experiments were conducted to evaluate the efficiency and effectiveness of this method, especially in the context of greenhouse detection and management.Results: Our findings indicate that the use of embedding vectors facilitates rapid convergence and significantly boosts segmentation accuracy and robustness. Notably, our method achieves or exceeds the performance of traditional segmentation models using only about 40% of the annotated samples. This reduction in the reliance on manual annotation has significant implications for remote sensing applications.Discussion: The application of VFMs in remote sensing tasks, particularly for greenhouse detection and management, demonstrated enhanced segmentation accuracy and reduced dependence on annotated samples. This method adapts more swiftly to different lighting conditions, enabling more precise monitoring of agricultural resources. Our study underscores the potential of VFMs in remote sensing tasks and opens new avenues for the expansive application of these models in diverse downstream tasks. |
| WOS研究方向 | Environmental Sciences & Ecology |
| WOS记录号 | WOS:001289012200001 |
| 出版者 | FRONTIERS MEDIA SA |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/206924]  |
| 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 | Liu, Tang |
| 作者单位 | 1.Prov Geomat Ctr Jiangsu, Nanjing, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Lu, Yuxiang,Wang, Jiahe,Wang, Dan,et al. Efficient greenhouse segmentation with visual foundation models: achieving more with fewer samples[J]. FRONTIERS IN ENVIRONMENTAL SCIENCE,2024,12:1395337. |
| APA | Lu, Yuxiang,Wang, Jiahe,Wang, Dan,&Liu, Tang.(2024).Efficient greenhouse segmentation with visual foundation models: achieving more with fewer samples.FRONTIERS IN ENVIRONMENTAL SCIENCE,12,1395337. |
| MLA | Lu, Yuxiang,et al."Efficient greenhouse segmentation with visual foundation models: achieving more with fewer samples".FRONTIERS IN ENVIRONMENTAL SCIENCE 12(2024):1395337. |
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。