计算机科学
分割
特征(语言学)
领域(数学分析)
人工智能
适应(眼睛)
学习迁移
传递关系
语义鸿沟
域适应
任务(项目管理)
模式识别(心理学)
遥感
图像(数学)
图像检索
地理
数学
哲学
数学分析
经济
管理
物理
光学
组合数学
分类器(UML)
语言学
作者
Hao Wang,Chao Tao,Jing Qi,Rong Xiao,Haifeng Li
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2022-01-01
卷期号:60: 1-15
被引量:3
标识
DOI:10.1109/tgrs.2022.3201688
摘要
Reducing the feature distribution shift caused by the factor of visual-environment changes, namely as VE-changes, is a hot issue in domain adaptation learning. However, in the semantic segmentation task of remote sensing imageries, besides VE-changes, the change of semantic-scenes (SS-changes) is another factor raising domain gap, which brings the label distribution shift. For example, although urban and rural share the same landcover label, there is still a gap in label distribution. If there is little relation that can be found in neither feature nor label space, forcibly adapting to a new domain could have a high risk of negative transfer. Hence, we propose a new Transitive Domain Adaptation method for Remote Sensing images (TDARS). Firstly, we introduce an intermediate domain to enlarge the relation between the given source and target domains. Secondly, we learn from primary and non-primary confident classes to increase the likelihood of transferring valuable information. As a result, TDARS enables the given source and target domains to be connected through the selected intermediate domain and performs effective knowledge transfer among all domains. The proposed method is evaluated on three domain adaptation datasets of remote sensing images. Extensive experiments show the approach can effectively handle the domain shift problem from remote sensing images compared to other state-of-the-art domain adaptation methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI