EUVIMEDEUVIMED entdecken
Crossref

MGNet: Learning Correspondences via Multiple Graphs

Dai Luanyuan, Xiaoyu Du, Hanwang Zhang, Jinhui Tang

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (4) · 3945-3953

DOI: 10.1609/aaai.v38i4.28187 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Dai Luanyuan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Learning correspondences aims to find correct correspondences (inliers) from the initial correspondence set with an uneven correspondence distribution and a low inlier rate, which can be regarded as graph data. Recent advances usually use graph neural networks (GNNs) to build a single type of graph or simply stack local graphs into the global one to complete the task. But they ignore the complementary relationship between different types of graphs, which can effectively capture potential relationships among sparse correspondences. To address this problem, we propose MGNet to effectively combine multiple complementary graphs. To obtain information integrating implicit and explicit local graphs, we construct local graphs from implicit and explicit aspects and combine them effectively, which is used to build a global graph. Moreover, we propose Graph Soft Degree Attention (GSDA) to make full use of all sparse correspondence information at once in the global graph, which can capture and amplify discriminative features. Extensive experiments demonstrate that MGNet outperforms state-of-the-art methods in different visual tasks. The code is provided in https://github.com/DAILUANYUAN/MGNet-2024AAAI.

Zitieren

APA

Luanyuan, D., Du, X., Zhang, H., & Tang, J. (2024). MGNet: Learning Correspondences via Multiple Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3945-3953. https://doi.org/10.1609/aaai.v38i4.28187

Vancouver

Luanyuan D, Du X, Zhang H, Tang J. MGNet: Learning Correspondences via Multiple Graphs. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(4):3945-3953. doi:10.1609/aaai.v38i4.28187

BibTeX
@article{Luanyuan2024,
  author = {Luanyuan, Dai and Du, Xiaoyu and Zhang, Hanwang and Tang, Jinhui},
  title = {MGNet: Learning Correspondences via Multiple Graphs},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {4},
  pages = {3945--3953},
  doi = {10.1609/aaai.v38i4.28187}
}
Kostenlos starten →