Hierarchical graph neural networks for visual clustering
US11860977B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | May 4, 2021 |
| Grant date | Jan 2, 2024 |
| Priority date | — |
| Expiry date | Jun 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.