Multilevel heterogeneous domain adaptation method for remote sensing image segmentation | |
Liang Chenbin; Cheng Bo; Xiao baihua; Dong Yunyun; Chen jinfen | |
发表期刊 | IEEE Transactions on Geoscience and Remote Sensing |
2023-01 | |
页码 | 61 |
摘要 | Due to more abundant data sources, more various objects of interest, and more time-consuming annotations, there is a large amount of out-of-distribution (OOD) data in the remote sensing field, on which the performance of high-accuracy image segmentation models trained under ideal experimental conditions generally degrades dramatically. Domain Adaptation (DA) consequently comes into being, which aims to learn the predictor for the label-scarce target domain of interest with the help of the label-sufficient source domain in the presence of the distribution difference, namely domain shift, between the two domains. However, the off-the-shelf DA methods for image segmentation not only struggle to cope with the more complex domain shift problems in remote sensing imagery, but also almost cannot process heterogeneous data directly without information loss. While the current heterogeneous DA methods mostly still rely on some supervision information from the target domain, which is typically inaccessible in the real world. To overcome these drawbacks, we propose the Multi-level Heterogeneous unsupervised DA method, termed MHDA, which unifies the instance-level DA based on cycle consistency, the feature-level DA based on contrastive learning, and the decision-level DA based on task consistency into a framework to more effectively handle the complex domain shift and heterogeneous data. After that, extensive DA experiments are conducted on the ISPRS dataset, the BigCity dataset constructed by ourselves, and the WHU dataset, in order to explore the effect of each module in MHDA, the necessity of heterogeneous DA, and the effectiveness of multi-level DA. And the results demonstrate that MHDA can achieve superior performance on the remote sensing image segmentation task, compared with several state-of-the-art DA methods. |
收录类别 | SCI |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51713 |
专题 | 复杂系统管理与控制国家重点实验室_影像分析与机器视觉 |
推荐引用方式 GB/T 7714 | Liang Chenbin,Cheng Bo,Xiao baihua,et al. Multilevel heterogeneous domain adaptation method for remote sensing image segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing,2023:61. |
APA | Liang Chenbin,Cheng Bo,Xiao baihua,Dong Yunyun,&Chen jinfen.(2023).Multilevel heterogeneous domain adaptation method for remote sensing image segmentation.IEEE Transactions on Geoscience and Remote Sensing,61. |
MLA | Liang Chenbin,et al."Multilevel heterogeneous domain adaptation method for remote sensing image segmentation".IEEE Transactions on Geoscience and Remote Sensing (2023):61. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Article0111.pdf(35677KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论