Papers › Learning Hierarchical Graph Neural Networks for Image Clustering

Learning Hierarchical Graph Neural Networks for Image Clustering

3 Jul 2021ICCV 2021 10arXiv:2107.01319archive 2025-07-28

Yifan Xing, Tong He, Tianjun Xiao, Yongxin Wang, Yuanjun Xiong, Wei Xia, David Wipf, Zheng Zhang, Stefano Soatto

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% improvement in F-score and 8% increase in Normalized Mutual Information (NMI) relative to current 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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

dmlc/dgl officialmentioned in paperpytorch report
dmlc/dgl officialpytorch report
djordjened92/cca-gnnclust mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClusteringFace ClusteringGraph Neural NetworkImage Clustering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Graph Neural NetworkHi-LANDER

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections