---
title: 'Hyperspectral Mamba: State-Space HSI Models'
url: https://www.emergentmind.com/topics/hyperspectral-mamba-hsm
type: topic
---

# Hyperspectral Mamba: State-Space HSI Models

Searching arXiv for recent papers on hyperspectral Mamba and closely related methods.
[Tool call suppressed in this environment: arXiv search used to verify relevant papers and dates.]
Hyperspectral Mamba denotes an emerging class of hyperspectral learning models that use Mamba or closely related selective state-space mechanisms to model spectral, spatial, or joint spectral-spatial dependencies in hyperspectral data. In the broad literature, the term functions as an umbrella for hyperspectral image classification, denoising, super-resolution, target detection, and tracking systems built around linear-complexity sequence modeling; in a narrow paper-specific sense, “Hyperspectral Mamba (HSM)” is also the name of a module introduced inside the HyMamba tracker for hyperspectral object tracking [2509.08265]. The category remains unsettled: the 2024 survey on hyperspectral image classification acknowledges Mamba only indirectly through citations such as SpectralMamba and does not define a dedicated HSM taxonomy, provide Mamba equations, or report Mamba experiments [2404.14955].

## 1. Nomenclature and scope

The literature uses “Hyperspectral Mamba” in two overlapping ways. First, it denotes a research family that adapts Mamba or selective state-space modeling to hyperspectral data. Second, it refers explicitly to the HSM module inside HyMamba, where three directional scanning SSMs are used to learn spatial and spectral information synchronously for hyperspectral object tracking [2509.08265]. This ambiguity is substantive rather than terminological: some papers present full hyperspectral backbones built around Mamba, whereas others insert Mamba into a hybrid pipeline alongside CNNs, Transformers, graph operators, wavelets, or adapters.

A concise task-level view of representative systems is as follows.

| Model | Task | Distinctive mechanism |
|---|---|---|
| SpectralMamba [2404.08489] | HSI classification | GSSM + PSS + selective SSM on spectral chunks |
| SS-Mamba [2404.18401] | HSI classification | Dual spectral/spatial token streams with center-guided enhancement |
| MiM [2405.12003] | HSI classification | Centralized MCS + T-Mamba + WMF |
| DualMamba [2406.07050] | HSI classification | Parallel Mamba/CNN global-local design |
| HSIDMamba [2404.09697] | HSI denoising | Bidirectional continuous scanning with eight directions |
| HSRMamba [2501.18500] | HSISR | Local 3D partitioning + global spectral reordering |
| HSRMamba [2505.11062] | SHSR | Wavelet decomposition + stripe scanning |
| SpecMamba [2604.05562] | Few-shot HTD | DCT Mamba adapter + PGTE + SSPLM |
| HyMamba / HSM [2509.08265] | Hyperspectral tracking | SSI with forward, backward, and spectral SSMs |

This scope also includes graph-augmented and wavelet-augmented systems such as GraphMamba and WaveMamba, which position Mamba as one component in a broader hyperspectral modeling stack [2407.08255; 2408.01231]. A plausible implication is that HSM is less a single architecture than a design space centered on state-space sequence modeling under hyperspectral structural constraints.

## 2. Mathematical basis and recurrent design principles

Most hyperspectral Mamba papers retain the classical state-space foundation
\[
h'(t)=\mathbf{A}h(t)+\mathbf{B}x(t), \qquad y(t)=\mathbf{C}h(t),
\]
together with zero-order-hold discretization and the recurrent form
\[
h_t=\overline{\mathbf{A}}h_{t-1}+\overline{\mathbf{B}}x_t,\qquad y_t=\mathbf{C}h_t,
\]
or closely related equivalents [2404.18401; 2404.08489]. Hyperspectral inputs are typically written as cubes such as
\[
x \in \mathbb{R}^{H \times W \times B}
\]
or analogous notation with \(V\) or \(C\) spectral channels, and the central modeling question is how to convert that cube into a sequence whose ordering preserves the dependencies that matter for the target task [2410.05100; 2604.05562].

The distinctive contribution of most HSM systems is therefore not a new state equation, but a new **deployment strategy for selective state-space modeling**. SpectralMamba uses a standard selective SSM inside a pipeline composed of Gated Spatial-Spectral Merging and Piece-wise Sequential Scanning, thereby treating the spectral axis as the primary sequence while compressing it into chunks [2404.08489]. IGroupSS-Mamba likewise keeps the S6 formulation but alters its use through interval grouping and direction assignment, applying one unidirectional S6 to each non-overlapping interval group rather than scanning all channels in all directions [2410.05100]. MiM preserves the selective Mamba operator but wraps it in center-oriented scan construction, Gaussian masking, semantic token learning, and multi-scale supervision [2405.12003].

A recurring principle is that hyperspectral Mamba systems treat the sequence itself as a learned or engineered object. This is visible in spectral chunking, grouped directional scans, bidirectional continuous scans, stripe scans, and sparse deformable sequencing. The literature therefore suggests that, in hyperspectral settings, Mamba effectiveness depends at least as much on sequence formation and inductive bias as on the internal SSM recurrence.

## 3. Sequence construction as the central design problem

Sequence construction is the most persistent technical theme in hyperspectral Mamba work. SpectralMamba reduces sequence length by splitting a spectral vector into contiguous pieces through Piece-wise Sequential Scanning, so that the original spectral length \(L\) becomes a sequence of \(R\) chunk tokens of width \(C\), preserving short-range context within each chunk and long-range context across chunks [2404.08489]. SS-Mamba instead generates two explicit token sets—spatial tokens from the whole patch and spectral tokens from a center subcube—then processes them in parallel Mamba branches [2404.18401].

MiM makes sequence order center-aware. Its centralized Mamba-Cross-Scan constructs four scan types, each split into two sub-sequences that begin at opposite sides of the patch and terminate at the center pixel, so the center becomes the final aggregation point for both directional branches [2405.12003]. HSIDMamba generalizes scanning in another direction: it serializes features by a bidirectional continuous scanning mechanism with forward and backward continuous scans from eight directions, then fuses the directional outputs with residual and spectral attention modules [2404.09697].

Later work pushes sequence design further into hyperspectral-specific priors. HSRMamba for single-image hyperspectral super-resolution introduces local 3D spatial-spectral partitioning and global spectral reordering, arguing that naive 1D serialization destroys local adjacency and that Mamba is highly sensitive to input order [2501.18500]. IGroupSS-Mamba partitions channels by interval—channels \(1,5,9,\ldots\) in one group, \(2,6,10,\ldots\) in another—and assigns left-to-right, right-to-left, top-to-bottom, and bottom-to-top scans to the four groups, reducing redundancy from adjacent-band similarity while preserving directional complementarity [2410.05100]. SDMamba treats sequence construction explicitly as adaptive selection: spatial and spectral tokens are ranked by angular similarity to an anchor token, sorted, sparsified by a ratio \(\lambda\), and only the retained ordered subset is sent to Mamba [2504.09446]. The wavelet-based HSRMamba for SHSR replaces global 1D visual scanning with fixed-length stripe scanning, arguing that stripe scanning introduces cross-window connections and better balances global and local modeling than either global 1D scans or disjoint windows [2505.11062].

Taken together, these designs suggest that “sequence engineering” is a defining trait of HSM. A plausible implication is that hyperspectral Mamba research has converged less on one canonical backbone than on a shared claim: the spectral-spatial cube should not be flattened naively.

## 4. Architectural families

One major family uses **dual-branch spectral-spatial factorization**. SS-Mamba generates spatial and spectral token sequences, processes them with two basic Mamba blocks, and couples them through a spectral-spatial feature enhancement module derived from center-region information [2404.18401]. DualMamba follows the same separation but assigns roles asymmetrically: a lightweight spectral/spatial Mamba branch extracts global features, a residual convolution branch extracts local features, and adaptive global-local fusion combines them dynamically [2406.07050]. WaveMamba extends this factorization with separate spatial and spectral gates followed by Haar wavelet decomposition of both branches before state-space modeling [2408.01231].

A second family uses **preconditioning modules before Mamba**. SpectralMamba learns a dynamic spatial-spectral mask by depthwise and pointwise convolutions to merge a local patch into one spectrum, then applies selective SSM to chunked spectral tokens [2404.08489]. MiM uses Gaussian Decay Mask to suppress peripheral interference after directional Mamba encoding and then learns compact semantic tokens through STL and STF [2405.12003]. GraphMamba combines HyperMamba or state-space-style sequence learning with graph-based spatial context, using weighted multi-hop aggregation in one version and token prioritization plus graph affinity and cross-attention in another [2407.08255; 2502.06427].

A third family is **frequency-aware or wavelet-aware HSM**. WaveMamba uses fixed Haar wavelets to produce \(ll\), \(lh\), \(hl\), and \(hh\) subbands from gated spatial and spectral features before feeding the fused representation into a state-space recurrence [2408.01231]. The SHSR-oriented HSRMamba uses discrete wavelet transform to split low-frequency spectral structure from high-frequency spatial detail, then assigns VSSM-based global modeling and local convolutional processing to dedicated branches [2505.11062]. SpecMamba shifts frequency awareness into few-shot target detection by applying DCT along the spectral dimension, grouping coefficients into low-, mid-, and high-frequency bands, and using a Mamba-based adapter on top of frozen Transformer representations [2604.05562].

A fourth family is **task-specialized state propagation**. HSIDMamba uses hyperspectral continuous scan blocks for denoising, with bidirectional continuous scanning, residual refinement, and channel attention [2404.09697]. HSRMamba for super-resolution uses contextual spatial-spectral Mamba groups that alternate local structured scans and globally reordered scans [2501.18500]. HyMamba places HSM inside Spectral State Integration so that forward, backward, and spectral hidden states are propagated across network depth and across video frames for tracking [2509.08265].

## 5. Empirical record across tasks

In hyperspectral image classification, several HSM systems report state-of-the-art or near-state-of-the-art results under their own protocols. SpectralMamba reports patchwise OA values of **89.52** on Houston2013, **77.90** on Augsburg, **92.48** on Longkou, and **97.66** on Botswana, with markedly low MACs and parameter counts relative to the compared RNN and Transformer baselines [2404.08489]. SS-Mamba reports **OA = 91.59 ± 1.85** on Indian Pines, **96.40 ± 2.27** on Pavia University, and **94.30 ± 1.10** on Houston, and its sequence-model ablation finds Mamba stronger than LSTM, GRU, and Transformer within the same spectral-spatial framework [2404.18401]. DualMamba reports **OA 99.23%**, **99.66%**, and **97.47%** on Indian Pines, WHU-Hi-Longkou, and Houston 2018 while using **72.94K**, **82.86K**, and **58.23K** parameters, respectively, and the fewest FLOPs among the compared methods [2406.07050]. IGroupSS-Mamba reports **OA 98.71** on Indian Pines, **99.75** on Pavia University, and **99.45** on Houston 2013 with only about **0.057 M** parameters and **0.0095 G** FLOPs [2410.05100]. SDMamba reports **OA = 99.44** on Indian Pines and **99.14** on Pavia University, and its sparsity ablation reduces FLOPs from **416.23M** to **172.41M** in the reported comparison [2504.09446]. MiM reports **OA = 92.0794**, **91.5756**, and **92.8917** on Indian Pines, Pavia University, and Houston 2013, respectively, while outperforming vanilla ViM and several Transformer baselines under fixed and disjoint splits [2405.12003].

For denoising and super-resolution, the empirical record is similarly task-specific. HSIDMamba reports **41.30 dB / 0.9950 / 0.0459** on the ICVL “Mixture” setting and, on CAVE at \(512\times512\times31\), **0.68M parameters**, **0.77 s** runtime, and **35.99 PSNR / 0.9867 SSIM / 0.3221 SAM**, outperforming recent Transformer baselines in the reported table [2404.09697]. The contextual HSRMamba reports, on Chikusei at \(\times4\), **PSNR 40.2781**, **SSIM 0.9441**, **SAM 2.3160**, **CC 0.9557**, and **ERGAS 5.0131**, and on Houston at \(\times4\), **PSNR 46.9653**, **SSIM 0.9838**, **SAM 1.6577**, **CC 0.9891**, and **ERGAS 1.8277** [2501.18500]. The wavelet-stripe HSRMamba states that it outperforms existing methods and reduces computational load and model size, but the provided excerpt does not include benchmark numbers beyond that qualitative claim [2505.11062].

For target detection and tracking, SpecMamba and HyMamba extend HSM beyond pixel classification. SpecMamba reports the highest \(AUC_{(P_f,P_d)}\) on all four reported datasets—**0.99927** on San Diego I, **0.98915** on San Diego II, **0.99994** on Cri, and **0.99942** on Urban-1—and strong cross-domain performance through DCTMA, PGTE, and SSPLM [2604.05562]. HyMamba reports **73.0\%** AUC and **96.3\%** DP@20 on HOTC2020, and its ablations show that replacing the simpler MM with HSM inside SSI improves AUC from **0.711** to **0.730** and DP@20 from **0.934** to **0.963** [2509.08265].

These results are not directly comparable across datasets, sampling protocols, or tasks. What they do show consistently is that hyperspectral Mamba systems are no longer confined to classification and now span restoration, detection, and tracking with task-specific sequence designs.

## 6. Limitations, ambiguities, and open directions

The most immediate limitation is taxonomic. The survey that frames the evolution of hyperspectral classification does not actually survey Mamba in depth, does not define HSM, and does not provide Mamba experiments or equations, so the category remains only partially institutionalized in the broader HSI literature [2404.14955]. This helps explain why “Hyperspectral Mamba” can mean a general family in one context and a tracking submodule in another [2509.08265].

A second limitation is methodological heterogeneity. Not every “Mamba” paper in this space implements canonical selective state-space modeling. HSIMamba is explicitly Mamba-inspired but does not instantiate the standard selective SSM formulation and instead uses bidirectional Conv1d pathways with learned matrices \(A\) and \(B\) plus a spatial block [2404.00272]. The hybrid GraphMamba paper from 2025 is framed as state-space/Mamba-based, but the explicit recurrence written in the paper is GRU-style rather than canonical selective scan [2502.06427]. WaveMamba presents a simplified state-space recurrence and omits the usual Mamba-specific selective-scan equations, token-order details, and several implementation specifics [2408.01231]. These cases indicate that HSM is partly a branding layer over a broader state-space design space.

A third limitation is reproducibility and specification. Several papers leave out exact scan-order formulas, parameter counts, or efficiency breakdowns. SpecMamba emphasizes parameter-efficient adaptation but does not report FLOPs, latency, or exact trainable parameter counts in the provided description [2604.05562]. HyMamba reports strong tracking accuracy but does not provide parameter count, FLOPs, FPS, or memory usage in the excerpt [2509.08265]. Even strong classification papers can contain partial inconsistencies: WaveMamba’s abstract claims a **4.5\%** improvement on Houston and **2.0\%** on Pavia, but the main benchmark tables in the provided description do not support those margins relative to the strongest listed baseline [2408.01231]. There is also a naming ambiguity: two distinct 2025 super-resolution papers are both titled “HSRMamba,” but they use materially different mechanisms—contextual spatial-spectral partitioning and reordering in one case, wavelet stripe state-space modeling in the other [2501.18500; 2505.11062].

The technical direction of travel is nevertheless clear. The literature increasingly couples Mamba with **frequency-domain structure**, **wavelets**, **graph context**, **physical priors**, **test-time adaptation**, and **hybrid global-local fusion** rather than using Mamba as a monolithic substitute for attention. This suggests that future HSM systems are likely to remain hybrid. A plausible implication is that the most durable contribution of hyperspectral Mamba research may not be a single canonical backbone, but a set of design rules: respect spectral continuity, engineer scan order explicitly, preserve local 3D structure, and combine linear-complexity state propagation with domain-specific priors when labels are scarce or domain shift is severe.

Source: https://www.emergentmind.com/topics/hyperspectral-mamba-hsm