Adaptive Homophily Clustering: Structure Homophily Graph Learning with Adaptive Filter for Hyperspectral Image

TL;DR

This paper introduces an adaptive homophily graph learning clustering method for hyperspectral images that enhances structural information utilization, feature representation, and graph updating, leading to improved clustering accuracy and robustness.

Contribution

The proposed AHSGC method innovatively combines adaptive filtering, homophily structure learning, and self-training to improve hyperspectral image clustering performance.

Findings

Achieves high clustering accuracy on hyperspectral datasets

Demonstrates low computational complexity and robustness

Outperforms existing methods in comparative experiments

Abstract

Hyperspectral image (HSI) clustering has been a fundamental but challenging task with zero training labels. Currently, some deep graph clustering methods have been successfully explored for HSI due to their outstanding performance in effective spatial structural information encoding. Nevertheless, insufficient structural information utilization, poor feature presentation ability, and weak graph update capability limit their performance. Thus, in this paper, a homophily structure graph learning with an adaptive filter clustering method (AHSGC) for HSI is proposed. Specifically, homogeneous region generation is first developed for HSI processing and constructing the original graph. Afterward, an adaptive filter graph encoder is designed to adaptively capture the high and low frequency features on the graph for subsequence processing. Then, a graph embedding clustering self-training decoder is developed with KL Divergence, with which the pseudo-label is generated for network training. Meanwhile, homophily-enhanced structure learning is introduced to update the graph according to the clustering task, in which the orient correlation estimation is adopted to estimate the node connection, and graph edge sparsification is designed to adjust the edges in the graph dynamically. Finally, a joint network optimization is introduced to achieve network self-training and update the graph. The K-means is adopted to express the latent features. Extensive experiments and repeated comparative analysis have verified that our AHSGC contains high clustering accuracy, low computational complexity, and strong robustness. The code source will be available at https://github.com/DY-HYX.