Ensemble Quadratic Assignment Network for Graph Matching
文献类型：期刊论文
| 作者 | Tan, Haoru1,2 ; Wang, Chuang1,2; Wu, Sitong2; Zhang, Xu-Yao1,2; Yin, Fei1,2; Liu, Cheng-Lin1,2
|
| 刊名 | INTERNATIONAL JOURNAL OF COMPUTER VISION
 |
| 出版日期 | 2024-04-13 |
| 页码 | 23 |
| 关键词 | Graph matching Combinatorial optimization Graph neural network Ensemble learning |
| ISSN号 | 0920-5691 |
| DOI | 10.1007/s11263-024-02040-8 |
| 通讯作者 | Wang, Chuang(chuang.wang@nlpr.ia.ac.cn) |
| 英文摘要 | Graph matching is a commonly used technique in computer vision and pattern recognition. Recent data-driven approaches have improved the graph matching accuracy remarkably, whereas some traditional algorithm-based methods are more robust to feature noises, outlier nodes, and global transformation (e.g. rotation). In this paper, we propose a graph neural network (GNN) based approach to combine the advantage of data-driven and traditional methods. In the GNN framework, we transform traditional graph matching solvers as single-channel GNNs on the association graph and extend the single-channel architecture to the multi-channel network. The proposed model can be seen as an ensemble method that fuses multiple algorithms at every iteration. Instead of averaging the estimates at the end of the ensemble, in our approach, the independent iterations of the ensembled algorithms exchange their information after each iteration via a 1x1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$1\,\times \,1$$\end{document} channel-wise convolution layer. Experiments show that our model improves the performance of traditional algorithms significantly. In addition, we propose a random sampling strategy to reduce the computational complexity and GPU memory usage, so that the model is applicable to matching graphs with thousands of nodes. We evaluate the performance of our method on three tasks: geometric graph matching, semantic feature matching, and few-shot 3D shape classification. The proposed model performs comparably or outperforms the best existing GNN-based methods. |
| WOS关键词 | RECOGNITION ; TRACKING |
| 资助项目 | National Natural Science Foundation of China[2018AAA0100400] ; Major Project for New Generation of AI[U20A20223] ; Major Project for New Generation of AI[61836014] ; Major Project for New Generation of AI[61721004] ; National Natural Science Foundation of China (NSFC)[2019141] ; Youth Innovation Promotion Association of CAS[Y9S9MS08] ; Youth Innovation Promotion Association of CAS[Y9J9MS08] ; Youth Innovation Promotion Association of CAS[E2S40101] ; Pioneer Hundred Talents Program of CAS |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001201483600002 |
| 出版者 | SPRINGER |
| 资助机构 | National Natural Science Foundation of China ; Major Project for New Generation of AI ; National Natural Science Foundation of China (NSFC) ; Youth Innovation Promotion Association of CAS ; Pioneer Hundred Talents Program of CAS |
| 源URL | [http://ir.ia.ac.cn/handle/173211/58268]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_模式分析与学习团队 |
| 通讯作者 | Wang, Chuang |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100044, Peoples R China |
| 推荐引用方式 GB/T 7714 | Tan, Haoru,Wang, Chuang,Wu, Sitong,et al. Ensemble Quadratic Assignment Network for Graph Matching[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2024:23. |
| APA | Tan, Haoru,Wang, Chuang,Wu, Sitong,Zhang, Xu-Yao,Yin, Fei,&Liu, Cheng-Lin.(2024).Ensemble Quadratic Assignment Network for Graph Matching.INTERNATIONAL JOURNAL OF COMPUTER VISION,23. |
| MLA | Tan, Haoru,et al."Ensemble Quadratic Assignment Network for Graph Matching".INTERNATIONAL JOURNAL OF COMPUTER VISION (2024):23. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。