HTCViT: an effective network for image classification and segmentation based on natural disaster datasets

doi:10.1007/s00371-023-02954-3

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

	HTCViT: an effective network for image classification and segmentation based on natural disaster datasets
	Ma, Zhihao 2,3; Li, Wei 2,3; Zhang, Muyang 2,3; Meng, Weiliang 1,2,3; Xu, Shibiao 4; Zhang, Xiaopeng 1,2,3
刊名	VISUAL COMPUTER
	2023-07-04
页码	13
关键词	Natural disaster image analysis Vision transformer Convolution Hierarchical
ISSN号	0178-2789
DOI	10.1007/s00371-023-02954-3
通讯作者	Meng, Weiliang(weiliang.meng@ia.ac.cn) ; Xu, Shibiao(shibiaoxu@bupt.edu.cn)
英文摘要	Classifying and segmenting natural disaster images are crucial for predicting and responding to disasters. However, current convolutional networks perform poorly in processing natural disaster images, and there are few proprietary networks for this task. To address the varying scales of the region of interest (ROI) in these images, we propose the Hierarchical TSAM-CB-ViT (HTCViT) network, which builds on the ViT network's attention mechanism to better process natural disaster images. Considering that ViT excels at extracting global context but struggles with local features, our method combines the strengths of ViT and convolution, and can capture overall contextual information within each patch using the Triple-Strip Attention Mechanism (TSAM) structure. Experiments validate that our HTCViT can improve the classification task with 3 - 4% and the segmentation task with 1 - 2% on natural disaster datasets compared to the vanilla ViT network.
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] ; Open Research Projects of ZhejiangLab[2021KE0AB07] ; [TC210H00L/42]
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:001025049000002
资助机构	National Natural Science Foundation of China ; Open Research Projects of ZhejiangLab
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53648]
专题	多模态人工智能系统全国重点实验室
通讯作者	Meng, Weiliang; Xu, Shibiao
作者单位	1.Zhejiang Lab, Hangzhou, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China 4.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ma, Zhihao,Li, Wei,Zhang, Muyang,et al. HTCViT: an effective network for image classification and segmentation based on natural disaster datasets[J]. VISUAL COMPUTER,2023:13.
APA	Ma, Zhihao,Li, Wei,Zhang, Muyang,Meng, Weiliang,Xu, Shibiao,&Zhang, Xiaopeng.(2023).HTCViT: an effective network for image classification and segmentation based on natural disaster datasets.VISUAL COMPUTER,13.
MLA	Ma, Zhihao,et al."HTCViT: an effective network for image classification and segmentation based on natural disaster datasets".VISUAL COMPUTER (2023):13.