Dynamic High-Resolution Network for Semantic Segmentation in Remote-Sensing Images

doi:10.3390/rs15092293

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Dynamic High-Resolution Network for Semantic Segmentation in Remote-Sensing Images
	Guo, Shichen 2,3; Yang, Qi 1,3; Xiang, Shiming 1,3; Wang, Pengfei 2; Wang, Xuezhi 2
刊名	REMOTE SENSING
	2023-04-26
卷号	15 期号:9 页码:28
关键词	semantic segmentation remote-sensing image neural architecture search sparse regularization HRNet
DOI	10.3390/rs15092293
通讯作者	Wang, Xuezhi(wxz@cnic.cn)
英文摘要	Semantic segmentation of remote-sensing (RS) images is one of the most fundamental tasks in the understanding of a remote-sensing scene. However, high-resolution RS images contain plentiful detailed information about ground objects, which scatter everywhere spatially and have variable sizes, styles, and visual appearances. Due to the high similarity between classes and diversity within classes, it is challenging to obtain satisfactory and accurate semantic segmentation results. This paper proposes a Dynamic High-Resolution Network (DyHRNet) to solve this problem. Our proposed network takes HRNet as a super-architecture, aiming to leverage the important connections and channels by further investigating the parallel streams at different resolution representations of the original HRNet. The learning task is conducted under the framework of a neural architecture search (NAS) and channel-wise attention module. Specifically, the Accelerated Proximal Gradient (APG) algorithm is introduced to iteratively solve the sparse regularization subproblem from the perspective of neural architecture search. In this way, valuable connections are selected for cross-resolution feature fusion. In addition, a channel-wise attention module is designed to weight the channel contributions for feature aggregation. Finally, DyHRNet fully realizes the dynamic advantages of data adaptability by combining the APG algorithm and channel-wise attention module simultaneously. Compared with nine classical or state-of-the-art models (FCN, UNet, PSPNet, DeepLabV3+, OCRNet, SETR, SegFormer, HRNet+FCN, and HRNet+OCR), DyHRNet has shown high performance on three public challenging RS image datasets (Vaihingen, Potsdam, and LoveDA). Furthermore, the visual segmentation results, the learned structures, the iteration process analysis, and the ablation study all demonstrate the effectiveness of our proposed model.
资助项目	Key Research Program of Frontier Sciences, CAS[ZDBS-LY-DQC016] ; National Key Research and Development Program of China[2022YFF1301803] ; National Natural Science Foundation of China (NSFC)[62076242]
WOS关键词	NEURAL ARCHITECTURE SEARCH ; FRAMEWORK
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	MDPI
WOS记录号	WOS:000987311100001
资助机构	Key Research Program of Frontier Sciences, CAS ; National Key Research and Development Program of China ; National Natural Science Foundation of China (NSFC)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53269]
专题	多模态人工智能系统全国重点实验室
通讯作者	Wang, Xuezhi
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Comp Network Informat Ctr, Beijing 100083, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Guo, Shichen,Yang, Qi,Xiang, Shiming,et al. Dynamic High-Resolution Network for Semantic Segmentation in Remote-Sensing Images[J]. REMOTE SENSING,2023,15(9):28.
APA	Guo, Shichen,Yang, Qi,Xiang, Shiming,Wang, Pengfei,&Wang, Xuezhi.(2023).Dynamic High-Resolution Network for Semantic Segmentation in Remote-Sensing Images.REMOTE SENSING,15(9),28.
MLA	Guo, Shichen,et al."Dynamic High-Resolution Network for Semantic Segmentation in Remote-Sensing Images".REMOTE SENSING 15.9(2023):28.