EUVIMEDEUVIMED entdecken
Crossref

Learning With Partial and Noisy Correspondence in Graph Matching

Yijie Lin, Mouxing Yang, Peng Hu, Jiancheng Lv, Hao Chen, Xi Peng

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-07 · 48 (7) · 8234-8249

DOI: 10.1109/tpami.2026.3670236 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-07. Verfasst von Yijie Lin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 81 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China, Sichuan Science and Technology Planning Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The success of existing graph matching methods heavily relies on high-quality training data with complete and precise correspondences between keypoints across different graphs. However, this assumption is often violated in real-world scenarios, leading to partial correspondence and noisy correspondence challenges. In brief, partial correspondence arises from viewpoint occlusions, where certain keypoints (i.e., outliers) lack valid counterparts in the target graph, while noisy correspondence refers to both incorrectly established (i.e., false positives) and neglected (i.e., false negatives) correspondences due to annotation error. In this paper, we propose the first unified framework to address both partial and noisy correspondence challenges in graph matching. Specifically, we introduce a dual-expert cooperative framework that integrates Koopmans-Beckmann and Lawler's quadratic assignment programming formulations (KB-QAP and L-QAP) through an align-fuse-refine pipeline. In the alignment stage, the KB-QAP expert aligns keypoints and distinguishes inliers from outliers using a novel quadratic contrastive loss. In the fusion stage, the L-QAP expert employs a graph transformer on the association graph to merge the aligned graphs and incorporates a learnable outlier-rejection mechanism to handle partial correspondences. Finally, by exploiting the different noise resistances of the two experts, we identify and refine the false positive and false negative correspondences, thereby enhancing robustness against noisy correspondence. Extensive experiments on four widely-used graph matching datasets demonstrate the effectiveness of our method against 17 competitive baselines in both partial and noisy correspondence scenarios.

Förderung

  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China
  • Sichuan Science and Technology Planning Project
  • Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China
  • System of Systems and Artificial Intelligence Laboratory Pioneer Fund

Zitieren

APA

Lin, Y., Yang, M., Hu, P., Lv, J., Chen, H., & Peng, X. (2026). Learning With Partial and Noisy Correspondence in Graph Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(7), 8234-8249. https://doi.org/10.1109/tpami.2026.3670236

Vancouver

Lin Y, Yang M, Hu P, Lv J, Chen H, Peng X. Learning With Partial and Noisy Correspondence in Graph Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(7):8234-8249. doi:10.1109/tpami.2026.3670236

BibTeX
@article{Lin2026,
  author = {Lin, Yijie and Yang, Mouxing and Hu, Peng and Lv, Jiancheng and Chen, Hao and Peng, Xi},
  title = {Learning With Partial and Noisy Correspondence in Graph Matching},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {7},
  pages = {8234--8249},
  doi = {10.1109/tpami.2026.3670236}
}
Kostenlos starten →