Triple-strip attention mechanism-based natural disaster images classification and segmentation

doi:10.1007/s00371-022-02535-w

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 三维可视计算

	Triple-strip attention mechanism-based natural disaster images classification and segmentation
	Ma, Zhihao 2,4; Yuan, Mengke 2,4; Gu, Jiaming 2,4; Meng, Weiliang 2,3,4; Xu, Shibiao 1; Zhang, Xiaopeng 2,3,4
刊名	VISUAL COMPUTER
	2022-06-18
页码	11
关键词	Natural disaster image analysis Image segmentation Attention mechanism
ISSN号	0178-2789
DOI	10.1007/s00371-022-02535-w
通讯作者	Meng, Weiliang(weiliang.meng@ia.ac.cn) ; Xu, Shibiao(shibiaoxu@bupt.edu.cn)
英文摘要	Fast and accurate semantic analysis of natural disaster images is crucial for rational rescue plans and resource allocation. However, the scarcity of meticulously labelled datasets and the ignorance of region-of-interest scale variations of popular general-purpose methods lead to undesirable performance. In this paper, we propose a novel triple-strip attention mechanism (TSAM) to solve the generalization problem of disaster images that can be combined into general networks. Our TSAM accumulates features of three parallel-strip attentions (row strip attention, column strip attention, and channel strip attention), and the output is multiplied with original input features for further processing. Our attention mechanism can effectively overcome the defect of ignoring global features caused by the convolution and enhance the performance of the network by weighting the features from both spatial and channel aspects more comprehensively. Besides, we employ both the compression and expansion operations in the weighting operation to reduce the amount of parameters, leading to negligible computational overhead. Experiments validate that our TSAM outperforms other state-of-the-art methods on natural disaster segmentation. Due to its concise form, plug-and-play pattern, and high promotion rate, our TSAM can be combined with many existing neural networks for better performance improvement.
资助项目	National Natural Science Foundation of China[U21A20515] ; National Natural Science Foundation of China[61972459] ; National Natural Science Foundation of China[62172416] ; National Natural Science Foundation of China[62102414] ; National Natural Science Foundation of China[U2003109] ; National Natural Science Foundation of China[62071157] ; National Natural Science Foundation of China[62171321] ; National Natural Science Foundation of China[62162044] ; National Natural Science Foundation of China[2021KE0AB07] ; National Natural Science Foundation of China[TC210H00L/42]
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000812611200001
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/49599]
专题	模式识别国家重点实验室_三维可视计算
通讯作者	Meng, Weiliang; Xu, Shibiao
作者单位	1.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Zhejiang Lab, Hangzhou, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ma, Zhihao,Yuan, Mengke,Gu, Jiaming,et al. Triple-strip attention mechanism-based natural disaster images classification and segmentation[J]. VISUAL COMPUTER,2022:11.
APA	Ma, Zhihao,Yuan, Mengke,Gu, Jiaming,Meng, Weiliang,Xu, Shibiao,&Zhang, Xiaopeng.(2022).Triple-strip attention mechanism-based natural disaster images classification and segmentation.VISUAL COMPUTER,11.
MLA	Ma, Zhihao,et al."Triple-strip attention mechanism-based natural disaster images classification and segmentation".VISUAL COMPUTER (2022):11.