# Token Clustering and Semantic Sequence Mamba for Hyperspectral Image Classification

arXiv: https://arxiv.org/abs/2609.28580 · HTML: https://mlsanity.com/paper/2609.28580/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Hyperspectral image analysis with Mamba, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Hyperspectral image analysis with Mamba](https://mlsanity.com/ssm/hyperspectral-image-analysis-with-mamba/)

## Builds on (most cited first, 24 of 24)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024)
- [Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2402.00789/) (2024)
- [QuadTree Attention for Vision Transformers](https://mlsanity.com/paper/2201.02767/) (2022)
- [Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer](https://mlsanity.com/paper/2204.08680/) (2022)
- [The Hidden Attention of Mamba Models](https://mlsanity.com/paper/2403.01590/) (2024)
- [MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2501.04944/) (2025)
- [FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification](https://mlsanity.com/paper/2011.05670/) (2020)
- [Spectral-Spatial Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2404.18401/) (2024)
- [Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classification](https://mlsanity.com/paper/2405.12003/) (2024)
- [DefMamba: Deformable Visual State Space Model](https://mlsanity.com/paper/2504.05794/) (2025)
- [RSDehamba: Lightweight Vision Mamba for Remote Sensing Satellite Image Dehazing](https://mlsanity.com/paper/2405.10030/) (2024)
- [RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing](https://mlsanity.com/paper/2503.10392/) (2025)
- [S2Mamba: A Spatial-spectral State Space Model for Hyperspectral Image Classification](https://mlsanity.com/paper/2404.18213/) (2024)
- [GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2407.08255/) (2024)
- [DAMamba: Vision State Space Model with Dynamic Adaptive Scan](https://mlsanity.com/paper/2502.12627/) (2025)
- [Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration](https://mlsanity.com/paper/2602.21917/) (2026)
- [Dual-Branch Subpixel-Guided Network for Hyperspectral Image Classification](https://mlsanity.com/paper/2412.03893/) (2024)
- [Sparse Deformable Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2504.09446/) (2025)
- [Hybrid State-Space and GRU-based Graph Tokenization Mamba for Hyperspectral Image Classification](https://mlsanity.com/paper/2502.06427/) (2025)
- [Hyperspectral Image Classification via Efficient Global Spectral Supertoken Clustering](https://mlsanity.com/paper/2604.27364/) (2026)
- [Pixel Ignores, Superpixel Sees: Adverse Weather Image Restoration via Semantic-Center SSM](https://mlsanity.com/paper/2608.01760/) (2026)

## Abstract (arXiv)

Although hyperspectral images (HSIs) provide rich spectral-spatial information, accurate pixel-level classification remains challenging because of spectral-spatial heterogeneity and complex spatial structures. Existing vision state space models (Mamba) typically construct sequences according to predefined spatial neighborhoods, without explicitly accounting for semantic similarity or spatial non-stationarity. To address this limitation, we propose Token Clustering and Semantic Sequence Mamba (STMamba), which organizes sparse tokens into semantically coherent sequences for hyperspectral image classification with the following features. First, at the macro level, a hierarchical encoder decoder progressively selects semantic tokens with the Token Clustering Module (TCM) and restores dense features using a parameter-free Cross-scale Neighborhood Attention (CNA) Upsampler. Second, at the micro level, TCM first identifies representative cluster centers through density-aware clustering and estimates soft memberships based on feature similarity. A quadtree-based dynamic selection strategy then retains sparse and spatially distributed tokens from each semantic cluster, forming coherent semantic-token sequences while reducing redundant pixel-wise representations. Third, parallel Spatial and Spectral Semantic-wise Sequencing Mamba (SWSM) modules capture complementary long-range spatial and spectral dependencies within homogeneous semantic token sequences while suppressing irrelevant interactions across heterogeneous regions. Experimental results on three large-scale benchmark datasets demonstrate that STMamba outperforms the SOTA methods with respect to quantitative and qualitative results.