Frank R. Schmidt

Universe Points Representation Learning for Partial Multi-Graph Matching

Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
AAAI Conference on Artificial Intelligence - Feb 2023
Download the publication: 11 MB 
Share the publication:
Many challenges from natural world can be formulated as a graph matching problem. Previous deep learning-based methods mainly consider a full two-graph matching setting. In this work, we study the more general partial matching problem with multi-graph cycle consistency guarantees. Building on a recent progress in deep learning on graphs, we propose a novel data-driven method (URL) for partial multi-graph matching, which uses an object-to-universe formulation and learns latent representations of abstract universe points. The proposed approach advances the state of the art in semantic keypoint matching problem, evaluated on Pascal VOC, CUB, and Willow datasets. Moreover, the set of controlled experiments on a synthetic graph matching dataset demonstrates the scalability of our method to graphs with large number of nodes and its robustness to high partiality.
This paper is also stored on arXiv.

Images and movies

teaser.png (47 KB)
 

BibTex references

@InProceedings\{NSB23,
  author       = "Nurlanov, Zhakshylyk and Schmidt, Frank R. and Bernard, Florian",
  title        = "Universe Points Representation Learning for Partial Multi-Graph Matching",
  booktitle    = "AAAI Conference on Artificial Intelligence",
  month        = "Feb",
  year         = "2023",
  publisher    = "{AAAI} Press",
  url          = "http://frank-r-schmidt.de/Publications/2023/NSB23"
}