Joint Superpixel and Self-Representation Learning for Scalable Hyperspectral Image Clustering

2025-09-28

AI Summary

Traditional hyperspectral image (HSI) clustering suffers from the decoupling of superpixel segmentation and clustering, as well as high computational complexity and poor scalability of subspace clustering methods. To address these issues, this paper proposes an end-to-end joint optimization framework. The method integrates a differentiable superpixel segmentation module enabling gradient backpropagation; a model-driven self-expression network incorporating an unrolled ADMM feedback mechanism, whereby the clustering objective dynamically guides superpixel generation; and per-superpixel compactness parameters to enhance spatial-spectral co-modeling. Evaluated on multiple benchmark HSI datasets, the proposed approach achieves significant improvements in clustering accuracy while maintaining high computational efficiency and scalability—outperforming state-of-the-art methods in both performance and practicality.

Technology Category

• Machine Learning: Clustering
• Computer Vision: Segmentation
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Subspace clustering is a powerful unsupervised approach for hyperspectral image (HSI) analysis, but its high computational and memory costs limit scalability. Superpixel segmentation can improve efficiency by reducing the number of data points to process. However, existing superpixel-based methods usually perform segmentation independently of the clustering task, often producing partitions that do not align with the subsequent clustering objective. To address this, we propose a unified end-to-end framework that jointly optimizes superpixel segmentation and subspace clustering. Its core is a feedback mechanism: a self-representation network based on unfolded Alternating Direction Method of Multipliers (ADMM) provides a model-driven signal to guide a differentiable superpixel module. This joint optimization yields clustering-aware partitions that preserve both spectral and spatial structure. Furthermore, our superpixel network learns a unique compactness parameter for each superpixel, enabling more flexible and adaptive segmentation. Extensive experiments on benchmark HSI datasets demonstrate that our method consistently achieves superior accuracy compared with state-of-the-art clustering approaches.

Problem

• Jointly optimizes superpixel segmentation and subspace clustering for hyperspectral images
• Addresses computational scalability limitations in unsupervised hyperspectral image analysis
• Integrates model-driven feedback to produce clustering-aware superpixel partitions

Innovation

• Joint optimization of superpixel segmentation and subspace clustering
• Feedback mechanism with self-representation network guiding superpixel module
• Learns unique compactness parameter for each superpixel adaptively