# Hyperspectral Image Classification via Efficient Global Spectral Supertoken Clustering

arXiv: https://arxiv.org/abs/2604.27364 · HTML: https://mlsanity.com/paper/2604.27364/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [Simple Hardware-Efficient Long Convolutions for Sequence Modeling](https://mlsanity.com/paper/2302.06646/) (2023)
- [MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2501.04944/) (2025)
- [Image as Set of Points](https://mlsanity.com/paper/2303.01494/) (2023)
- [FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification](https://mlsanity.com/paper/2011.05670/) (2020)
- [R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement](https://mlsanity.com/paper/2211.08609/) (2022)
- [NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2408.10178/) (2024)
- [DualMamba: A Lightweight Spectral-Spatial Mamba-Convolution Network for Hyperspectral Image Classification](https://mlsanity.com/paper/2406.07050/) (2024)
- [Neural Clustering based Visual Representation Learning](https://mlsanity.com/paper/2403.17409/) (2024)
- [TCFormer: Visual Recognition via Token Clustering Transformer](https://mlsanity.com/paper/2407.11321/) (2024)
- [Disentangled Representation with Dual-stage Feature Learning for Face Anti-spoofing](https://mlsanity.com/paper/2110.09157/) (2021)
- [S2Mamba: A Spatial-spectral State Space Model for Hyperspectral Image Classification](https://mlsanity.com/paper/2404.18213/) (2024)
- [Dual-stage Hyperspectral Image Classification Model with Spectral Supertoken](https://mlsanity.com/paper/2407.07307/) (2024)
- [Deep Diversity-Enhanced Feature Representation of Hyperspectral Images](https://mlsanity.com/paper/2301.06132/) (2023)
- [Content-driven Magnitude-Derivative Spectrum Complementary Learning for Hyperspectral Image Classification](https://mlsanity.com/paper/2407.18593/) (2024)

## Built on by (most cited first, 1 of 1)

- [Token Clustering and Semantic Sequence Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2609.28580/) (2026)

## Abstract (arXiv)

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.