EUVIMEDEUVIMED entdecken
Crossref

Contrastive Learning Network for Unsupervised Graph Matching

Yu Xie, Lianhang Luo, Tianpei Cao, Bin Yu, A. K. Qin

IEEE Transactions on Circuits and Systems for Video Technology · 2025-01 · 35 (1) · 643-656

DOI: 10.1109/tcsvt.2024.3457575 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-01. Verfasst von Yu Xie und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Key Research and Development Projects of Shaanxi Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph matching aims to establish node correspondences between graphs, which is a classic combinatorial optimization problem. In recent years, (deep) learning-based methods have emerged as a superior alternative to traditional graph matching solvers. However, these methods typically rely on node-level correspondence labels, which can be prohibitively expensive or unrealistic. Inspired by contrastive learning that is a prevalent paradigm for self-supervised representation learning, we develop a Contrastive Learning Network for Unsupervised Graph Matching (CUGM), which is an end-to-end differentiable pipeline to learn node permutations. Specifically, we propose three-level augmentation including raw image augmentation, graph augmentation and model augmentation for generating diverse enough contrastive views to enrich training instances. Then a contrastive learning network is constructed to capture the higher-order structural information in graphs and learn the final node representations for yielding the affinity matrix to directly solve a linear assignment problem. More importantly, we propose a node-level contrastive loss with false negative cancellation for optimizing the whole network to extract the tailored node feature representations to improve graph matching accuracy. Experimental results on standard graph matching benchmarks demonstrate that our end-to-end unsupervised method achieves the competitive performance compared with state-of-the-art supervised and unsupervised graph matching methods.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Key Research and Development Projects of Shaanxi Province
  • Shanxi Scholarship Council of China
  • Australian Research Council

Zitieren

APA

Xie, Y., Luo, L., Cao, T., Yu, B., & Qin, A. K. (2025). Contrastive Learning Network for Unsupervised Graph Matching. IEEE Transactions on Circuits and Systems for Video Technology, 35(1), 643-656. https://doi.org/10.1109/tcsvt.2024.3457575

Vancouver

Xie Y, Luo L, Cao T, Yu B, Qin AK. Contrastive Learning Network for Unsupervised Graph Matching. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(1):643-656. doi:10.1109/tcsvt.2024.3457575

BibTeX
@article{Xie2025,
  author = {Xie, Yu and Luo, Lianhang and Cao, Tianpei and Yu, Bin and Qin, A. K.},
  title = {Contrastive Learning Network for Unsupervised Graph Matching},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {1},
  pages = {643--656},
  doi = {10.1109/tcsvt.2024.3457575}
}
Kostenlos starten →