EUVIMEDEUVIMED entdecken
Crossref

Learnable Graph Matching: A Practical Paradigm for Data Association

Jiawei He, Zehao Huang, Naiyan Wang, Zhaoxiang Zhang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-07 · 46 (7) · 4880-4895

DOI: 10.1109/tpami.2024.3362401 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-07. Verfasst von Jiawei He und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 116 Literaturangaben. Gefördert von: National Natural Science Foundation of China, 2035 Innovation Program of CAS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Natural Science Foundation of China
  • 2035 Innovation Program of CAS

Zitieren

APA

He, J., Huang, Z., Wang, N., & Zhang, Z. (2024). Learnable Graph Matching: A Practical Paradigm for Data Association. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(7), 4880-4895. https://doi.org/10.1109/tpami.2024.3362401

Vancouver

He J, Huang Z, Wang N, Zhang Z. Learnable Graph Matching: A Practical Paradigm for Data Association. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(7):4880-4895. doi:10.1109/tpami.2024.3362401

BibTeX
@article{He2024,
  author = {He, Jiawei and Huang, Zehao and Wang, Naiyan and Zhang, Zhaoxiang},
  title = {Learnable Graph Matching: A Practical Paradigm for Data Association},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {7},
  pages = {4880--4895},
  doi = {10.1109/tpami.2024.3362401}
}
Kostenlos starten →