Learning Hierarchical Graph Neural Networks for Image Clustering

by   Yifan Xing, et al.

We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities using a training set of images annotated with labels belonging to a disjoint set of identities. Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level. Unlike fully unsupervised hierarchical clustering, the choice of grouping and complexity criteria stems naturally from supervision in the training set. The resulting method, Hi-LANDER, achieves an average of 54 and 8 GNN-based clustering algorithms. Additionally, state-of-the-art GNN-based methods rely on separate models to predict linkage probabilities and node densities as intermediate steps of the clustering process. In contrast, our unified framework achieves a seven-fold decrease in computational cost. We release our training and inference code at https://github.com/dmlc/dgl/tree/master/examples/pytorch/hilander.


Supervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarization

Conventional methods for speaker diarization involve windowing an audio ...

A Potts model approach to unsupervised graph clustering with Graph Neural Networks

Numerous approaches have been explored for graph clustering, including t...

MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods

Domain decomposition methods (DDMs) are popular solvers for discretized ...

TrojanSAINT: Gate-Level Netlist Sampling-Based Inductive Learning for Hardware Trojan Detection

We propose TrojanSAINT, a graph neural network (GNN)-based hardware Troj...

Robust Graph Neural Networks using Weighted Graph Laplacian

Graph neural network (GNN) is achieving remarkable performances in a var...

Hierarchical Inference of the Lensing Convergence from Photometric Catalogs with Bayesian Graph Neural Networks

We present a Bayesian graph neural network (BGNN) that can estimate the ...

Automating Style Analysis and Visualization With Explainable AI – Case Studies on Brand Recognition

Incorporating style-related objectives into shape design has been centra...

Please sign up or login with your details

Forgot password? Click here to reset