Multi-level Graph Subspace Contrastive Learning for Hyperspectral Image Clustering

TL;DR

This paper introduces a multi-level graph contrastive learning framework for hyperspectral image clustering, effectively capturing global and local features to improve clustering accuracy significantly.

Contribution

The study proposes a novel multi-level graph subspace contrastive learning model that integrates spectral and texture features with attention-based pooling for enhanced HSI clustering.

Findings

Achieved high clustering accuracy on four HSI datasets.

Outperformed existing state-of-the-art clustering methods.

Demonstrated robustness of the proposed approach.

Abstract

Hyperspectral image (HSI) clustering is a challenging task due to its high complexity. Despite subspace clustering shows impressive performance for HSI, traditional methods tend to ignore the global-local interaction in HSI data. In this study, we proposed a multi-level graph subspace contrastive learning (MLGSC) for HSI clustering. The model is divided into the following main parts. Graph convolution subspace construction: utilizing spectral and texture feautures to construct two graph convolution views. Local-global graph representation: local graph representations were obtained by step-by-step convolutions and a more representative global graph representation was obtained using an attention-based pooling strategy. Multi-level graph subspace contrastive learning: multi-level contrastive learning was conducted to obtain local-global joint graph representations, to improve the consistency of the positive samples between views, and to obtain more robust graph embeddings. Specifically, graph-level contrastive learning is used to better learn global representations of HSI data. Node-level intra-view and inter-view contrastive learning is designed to learn joint representations of local regions of HSI. The proposed model is evaluated on four popular HSI datasets: Indian Pines, Pavia University, Houston, and Xu Zhou. The overall accuracies are 97.75%, 99.96%, 92.28%, and 95.73%, which significantly outperforms the current state-of-the-art clustering methods.