Learnable Graph Matching: A Practical Paradigm for Data Association | |
He, Jiawei1,2![]() ![]() | |
发表期刊 | IEEE Transactions on Pattern Analysis and Machine Intelligence
![]() |
2024-07 | |
卷号 | 46期号:7页码:4880-4895 |
摘要 | Data association is at the core of many computer vision tasks, e.g., multiple object tracking, image matching, and point cloud registration. however, current data association solutions have some defects: they mostly ignore the intra-view context information; besides, they either train deep association models in an end-to-end way and hardly utilize the advantage of optimization-based assignment methods, or only use an off-the-shelf neural network to extract features. In this paper, we propose a general learnable graph matching method to address these issues. Especially, we model the intra-view relationships as an undirected graph. Then data association turns into a general graph matching problem between graphs. Furthermore, to make optimization end-to-end differentiable, we relax the original graph matching problem into continuous quadratic programming and then incorporate training into a deep graph neural network with KKT conditions and implicit function theorem. In MOT task, our method achieves state-of-the-art performance on several MOT datasets. For image matching, our method outperforms state-of-the-art methods on a popular indoor dataset, ScanNet. For point cloud registration, we also achieve competitive results. |
关键词 | Graph matching data association multiple object tracking image matching |
DOI | 10.1109/TPAMI.2024.3362401 |
收录类别 | SCI |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | 环境多维感知 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57423 |
专题 | 模式识别实验室 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.Tusimple 4.Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences (HKISI_CAS) |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | He, Jiawei,Huang, Zehao,Wang, Naiyan,et al. Learnable Graph Matching: A Practical Paradigm for Data Association[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46(7):4880-4895. |
APA | He, Jiawei,Huang, Zehao,Wang, Naiyan,&Zhang, Zhaoxiang.(2024).Learnable Graph Matching: A Practical Paradigm for Data Association.IEEE Transactions on Pattern Analysis and Machine Intelligence,46(7),4880-4895. |
MLA | He, Jiawei,et al."Learnable Graph Matching: A Practical Paradigm for Data Association".IEEE Transactions on Pattern Analysis and Machine Intelligence 46.7(2024):4880-4895. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Learnable_Graph_Matc(3520KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论