Patent · US Active

Hierarchical graph neural networks for visual clustering

US11860977B1 · kind B1 · utility

1Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 4, 2021
Grant dateJan 2, 2024
Priority date
Expiry dateJun 24, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/82
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Techniques for performing visual clustering with a hierarchical graph neural network framework including a joint linkage prediction and density estimation graph model are described. Embodiments herein recurrently run the joint linkage prediction and density estimation graph model to generate intermediate clusters in multiple iterations (e.g., until convergence) to obtain a final clustering result. In certain embodiments, for each iteration, the input graph contains nodes that are merged from nodes assigned to intermediate clusters from the previous iteration. By using a small and fixed bandwidth k in each iteration, embodiments herein alleviate the sensitivity to the k selection for different clustering applications. Certain embodiments herein remove the tuning of a different k (e.g., k-bandwidth) for k-nearest neighbor graph construction over different clustering applications.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.