Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images

doi:10.3390/rs9050446

CASIA OpenIR > 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

	Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images
	Wang, Hongzhen1,2 ; Wang, Ying 1; Zhang, Qian3 ; Xiang, Shiming1 ; Pan, Chunhong1
发表期刊	REMOTE SENSING
	2017-05-01
卷号	9 期号:5 页码:446
文章类型	Article
摘要	Semantic segmentation is a fundamental task in remote sensing image processing. The large appearance variations of ground objects make this task quite challenging. Recently, deep convolutional neural networks (DCNNs) have shown outstanding performance in this task. A common strategy of these methods (e.g., SegNet) for performance improvement is to combine the feature maps learned at different DCNN layers. However, such a combination is usually implemented via feature map summation or concatenation, indicating that the features are considered indiscriminately. In fact, features at different positions contribute differently to the final performance. It is advantageous to automatically select adaptive features when merging different-layer feature maps. To achieve this goal, we propose a gated convolutional neural network to fulfill this task. Specifically, we explore the relationship between the information entropy of the feature maps and the label-error map, and then a gate mechanism is embedded to integrate the feature maps more effectively. The gate is implemented by the entropy maps, which are generated to assign adaptive weights to different feature maps as their relative importance. Generally, the entropy maps, i.e., the gates, guide the network to focus on the highly-uncertain pixels, where detailed information from lower layers is required to improve the separability of these pixels. The selected features are finally combined to feed into the classifier layer, which predicts the semantic label of each pixel. The proposed method achieves competitive segmentation accuracy on the public ISPRS 2D Semantic Labeling benchmark, which is challenging for segmentation by only using the RGB images.
关键词	Semantic Segmentation Cnn Deep Learning Isprs Remote Sensing Gate
WOS标题词	Science & Technology ; Technology
DOI	10.3390/rs9050446
关键词[WOS]	CLASSIFICATION
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(91646207 ; Beijing Natural Science Foundation(4162064) ; 91338202 ; 91438105)
WOS研究方向	Remote Sensing
WOS类目	Remote Sensing
WOS记录号	WOS:000402573700049
引用统计	被引频次：160[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/15117
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.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Alibaba Grp, Beijing 100102, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wang, Hongzhen,Wang, Ying,Zhang, Qian,et al. Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images[J]. REMOTE SENSING,2017,9(5):446.
APA	Wang, Hongzhen,Wang, Ying,Zhang, Qian,Xiang, Shiming,&Pan, Chunhong.(2017).Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images.REMOTE SENSING,9(5),446.
MLA	Wang, Hongzhen,et al."Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images".REMOTE SENSING 9.5(2017):446.

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
04_09-00446-v2_remot（2410KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载