Scene Recognition With Prototype-Agnostic Scene Layout

doi:10.1109/TIP.2020.2986599

	Scene Recognition With Prototype-Agnostic Scene Layout
	Chen, Gongwei 1; Song, Xinhang 1; Zeng, Haitao 2,3; Jiang, Shuqiang 1
	2020
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	29 页码:5877-5888
摘要	Exploiting the spatial structure in scene images is a key research direction for scene recognition. Due to the large intra-class structural diversity, building and modeling flexible structural layout to adapt various image characteristics is a challenge. Existing structural modeling methods in scene recognition either focus on predefined grids or rely on learned prototypes, which all have limited representative ability. In this paper, we propose Prototype-agnostic Scene Layout (PaSL) construction method to build the spatial structure for each image without conforming to any prototype. Our PaSL can flexibly capture the diverse spatial characteristic of scene images and have considerable generalization capability. Given a PaSL, we build Layout Graph Network (LGN) where regions in PaSL are defined as nodes and two kinds of independent relations between regions are encoded as edges. The LGN aims to incorporate two topological structures (formed in spatial and semantic similarity dimensions) into image representations through graph convolution. Extensive experiments show that our approach achieves state-of-the-art results on widely recognized MIT67 and SUN397 datasets without multi-model or multi-scale fusion. Moreover, we also conduct the experiments on one of the largest scale datasets, Places365. The results demonstrate the proposed method can be well generalized and obtains competitive performance.
关键词	Layout Semantics Prototypes Image recognition Convolution Neural networks Deformable models Scene classification convolution neural networks graph neural networks scene layout
DOI	10.1109/TIP.2020.2986599
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Project of New Generation Artificial Intelligence of China[2018AAA0102500] ; National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61902378] ; Beijing Natural Science Foundation[L182054] ; Beijing Natural Science Foundation[Z190020] ; National Program for Special Support of Eminent Professionals ; National Program for Support of Top-Notch Young Professionals ; Lenovo Outstanding Young Scientists Program ; National Postdoctoral Program for Innovative Talents[BX201700255]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000532260800007
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：37[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/15401
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Jiang, Shuqiang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.China Univ Min & Technol Beijing, Sch Mech Elect & Informat Engn, Beijing 100083, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Chen, Gongwei,Song, Xinhang,Zeng, Haitao,et al. Scene Recognition With Prototype-Agnostic Scene Layout[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:5877-5888.
APA	Chen, Gongwei,Song, Xinhang,Zeng, Haitao,&Jiang, Shuqiang.(2020).Scene Recognition With Prototype-Agnostic Scene Layout.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,5877-5888.
MLA	Chen, Gongwei,et al."Scene Recognition With Prototype-Agnostic Scene Layout".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):5877-5888.