Generic Scene Graph Generation Model with Hierarchical Prompt Learning

doi:10.1007/s11263-025-02499-z

	Generic Scene Graph Generation Model with Hierarchical Prompt Learning
	Zhu, Xuhan 1,2,3; Xing, Yifei 1,2,3; Wang, Ruiping 2,3; Wang, Yaowei 1; Lan, Xiangyuan 1
	2025-06-27
发表期刊	INTERNATIONAL JOURNAL OF COMPUTER VISION
ISSN	0920-5691
页码	19
摘要	Scene Graph Generation (SGG) delivers structured knowledge to represent complex scenes and has proven effective in many computer vision tasks. However, traditional SGG models suffer from two limitations that hinder their applicability for higher-level visual tasks: (1) a rigid structure that results in low efficiency and limited flexibility, and (2) biased optimization that results in biased predictions that favor uninformative predicates. To resolve these two issues, we propose GSGG (Generic Scene Graph Generation), a novel, efficient, and flexible SGG model that (1) combines generalized modules to construct top-performance and high-efficiency SGG model and (2) employs a prompt learning-based relation decoder with a novel Hierarchical Prompt (HP) learning method to mitigate biased optimization. HP utilizes the composition of basic prompts constrained to progressively narrowed class groups and encourages the corresponding prompts to focus on the learning of increasingly informative predicates. Extensive evaluations on three SGG benchmarks demonstrate the excellent efficiency and performance of GSGG with HP. We also introduce a novel predicate generalization task with a new benchmark, and experiments on it demonstrate the effectiveness of HP in base-to-novel predicate generalization.
关键词	Generic scene graph generation Hierarchical prompt learning Novel predicate generalization
DOI	10.1007/s11263-025-02499-z
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[PCL2023A08] ; Pengcheng Laboratory Research Project[U21B2025] ; Pengcheng Laboratory Research Project[62402252] ; National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001518315700001
出版者	SPRINGER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42304
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Ruiping; Lan, Xiangyuan
作者单位	1.Pengcheng Lab, Shenzhen 518000, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Xuhan,Xing, Yifei,Wang, Ruiping,et al. Generic Scene Graph Generation Model with Hierarchical Prompt Learning[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2025:19.
APA	Zhu, Xuhan,Xing, Yifei,Wang, Ruiping,Wang, Yaowei,&Lan, Xiangyuan.(2025).Generic Scene Graph Generation Model with Hierarchical Prompt Learning.INTERNATIONAL JOURNAL OF COMPUTER VISION,19.
MLA	Zhu, Xuhan,et al."Generic Scene Graph Generation Model with Hierarchical Prompt Learning".INTERNATIONAL JOURNAL OF COMPUTER VISION (2025):19.