Knowledge Commons of Institute of Automation,CAS
CMT: Cross Mean Teacher Unsupervised Domain Adaptation for VHR Image Semantic Segmentation | |
Liang Yan1,2; Bin Fan3; Shiming Xiang1,2; Chunhong Pan2 | |
发表期刊 | IEEE Geoscience and Remote Sensing Letters |
ISSN | 1558-0571 |
2021 | |
卷号 | 0期号:0页码:1-5 |
文章类型 | 科技论文 |
摘要 | Semantic segmentation of remote sensing images has achieved superior results with the supervised deep learning models. However, their performance to unseen data domains could be very bad due to the domain shift between different domains. Recently, a series of unsupervised domain adaptation (UDA) methods has been developed to solve the domain shift problem in semantic segmentation. Most of them use adversarial learning to achieve global cross-domain alignment and use a self-training (ST) strategy to generate pseudo-labels for classwise alignment. However, these methods ignore the pixels that are not assigned pseudo-labels. Those pixels are mostly at the boundaries, which are vital to the final segmentation results. To solve this problem, this letter proposes a cross mean teacher (CMT) UDA method. The whole framework consists of two parts. On the one hand, the global cross-domain distribution alignment is performed, and then, reliable pseudo-labels are assigned to the target data. On the other hand, a cross teacher-student network (CTSN) is developed to effectively use those pixels with and without pseudo-labels. This network contains two student networks (S₁ and S₂) and two teacher networks (T₁ and T₂) for cross-consistency constraints that supervises S₂ (or S₁) by the prediction results of T₁ (or T₂). The cross supervision by CTSN is helpful to prevent performance bottlenecks caused by the high coupling of teacher-student network in existing methods. Extensive experiments on three different remote sensing adaptation scenes verify the effectiveness and superiority of the proposed method. |
关键词 | Cross mean teacher (CMT) self-training (ST) semantic segmentation unsupervised domain adaptation (UDA) very-high-resolution (VHR) image |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1109/LGRS.2021.3065982 |
URL | 查看原文 |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:000732228300001 |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44708 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
作者单位 | 1.School of Artificial Intelligence Institute, University of Chinese Academy of Sciences 2.School of Automation and Electrical Engineering, University of Science and Technology Beijing 3.National Laboratory of Pattern Recognition, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Liang Yan,Bin Fan,Shiming Xiang,et al. CMT: Cross Mean Teacher Unsupervised Domain Adaptation for VHR Image Semantic Segmentation[J]. IEEE Geoscience and Remote Sensing Letters,2021,0(0):1-5. |
APA | Liang Yan,Bin Fan,Shiming Xiang,&Chunhong Pan.(2021).CMT: Cross Mean Teacher Unsupervised Domain Adaptation for VHR Image Semantic Segmentation.IEEE Geoscience and Remote Sensing Letters,0(0),1-5. |
MLA | Liang Yan,et al."CMT: Cross Mean Teacher Unsupervised Domain Adaptation for VHR Image Semantic Segmentation".IEEE Geoscience and Remote Sensing Letters 0.0(2021):1-5. |
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 | ||
CMT_ Cross Mean Teac(1700KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
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