Hyperspectral Image Classification via Efficient Global Spectral Supertoken Clustering

2026-04-29

AI Summary

This work addresses the challenge in hyperspectral image classification of simultaneously preserving regional consistency and boundary alignment, a limitation exacerbated by the inherent conflict between clustering and pixel-level classification in existing superpixel-based methods. To resolve this, we propose the Dual-stage Spectrally Constrained Clustering Classifier (DSCC), which decouples clustering from classification: first generating boundary-preserving spectral super-tokens based on spectral similarity and spatial proximity, then performing token-level prediction. The method incorporates density-isolated center selection, global multi-criterion feature distance, locally aware assignment regularization, and soft label encoding to significantly enhance robustness to mixed pixels and adaptability across scales. Evaluated on the WHU-OHS dataset, DSCC achieves a competitive CF1 score of 0.728 at an inference speed of 197.75 FPS, demonstrating superior accuracy–efficiency trade-offs compared to state-of-the-art approaches.

Abstract

Hyperspectral image classification demands spatially coherent predictions and precise boundary delineation. Yet prevailing superpixel-based methods face an inherent contradiction: clustering aggregates similar pixels into regions, but the subsequent classifier operates pixel-wise, undermining regional consistency. Consequently, existing approaches do not guarantee region-level, boundary-aligned classification. To address this limitation, we propose the Dual-stage Spectrum-Constrained Clustering-based Classifier (DSCC), an end-to-end framework that explicitly decouples clustering from classification by first grouping spectral similar and spatially proximate pixels into spectral supertokens and then performing token-level prediction. At its core, DSCC computes an image-level multi-criteria feature distance between pixels and centers, followed by a locality-aware assignment regularization, enabling the generation of boundary-preserving spectral supertokens. A density-isolation based center selection further yields representative, well-separated centers, reducing redundancy and improving robustness to scale variation. To accommodate mixed land-cover compositions within each token, we introduce a soft-label scheme that encodes class proportions and improves robustness for mixed-class tokens. DSCC attains a CF1 of 0.728 at 197.75 FPS on the WHU-OHS dataset, offering a superior accuracy-efficiency trade-off compared with state-of-the-art methods. Extensive experiments further validate the effectiveness and generality of the proposed dual-stage paradigm for hyperspectral image classification. The source code is available at https://github.com/laprf/DSCC.

Problem

• Hyperspectral Image Classification
• Superpixel
• Regional Consistency
• Boundary Delineation
• Spectral Clustering

Innovation

• spectral supertoken
• dual-stage clustering
• boundary-preserving classification
• soft-label scheme
• hyperspectral image classification