Pith. sign in

REVIEW 7 cited by

SpectralMamba: Efficient Mamba for Hyperspectral Image Classification

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.08489 v1 pith:5X7U7ELB submitted 2024-04-12 cs.CV

Jing Yao , Danfeng Hong , Chenyu Li , Jocelyn Chanussot This is my paper · ORCID
classification cs.CV
keywords spectralmambaefficientspacespectrumattentionclassificationhyperspectralimage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recurrent neural networks and Transformers have recently dominated most applications in hyperspectral (HS) imaging, owing to their capability to capture long-range dependencies from spectrum sequences. However, despite the success of these sequential architectures, the non-ignorable inefficiency caused by either difficulty in parallelization or computationally prohibitive attention still hinders their practicality, especially for large-scale observation in remote sensing scenarios. To address this issue, we herein propose SpectralMamba -- a novel state space model incorporated efficient deep learning framework for HS image classification. SpectralMamba features the simplified but adequate modeling of HS data dynamics at two levels. First, in spatial-spectral space, a dynamical mask is learned by efficient convolutions to simultaneously encode spatial regularity and spectral peculiarity, thus attenuating the spectral variability and confusion in discriminative representation learning. Second, the merged spectrum can then be efficiently operated in the hidden state space with all parameters learned input-dependent, yielding selectively focused responses without reliance on redundant attention or imparallelizable recurrence. To explore the room for further computational downsizing, a piece-wise scanning mechanism is employed in-between, transferring approximately continuous spectrum into sequences with squeezed length while maintaining short- and long-term contextual profiles among hundreds of bands. Through extensive experiments on four benchmark HS datasets acquired by satellite-, aircraft-, and UAV-borne imagers, SpectralMamba surprisingly creates promising win-wins from both performance and efficiency perspectives.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ECP-Mamba: An Efficient Multi-scale Self-supervised Contrastive Learning Method with State Space Model for PolSAR Image Classification

    cs.CV 2025-06 conditional novelty 6.0 of 10

    ECP-Mamba, a Mamba-based network with a spiral scan and multi-scale self-distillation, reports state-of-the-art PolSAR image classification accuracy at label rates as low as 0.2%.

  2. PNEC-Mamba: Prototype-Guided Positive-Negative Evidence Calibration for Hyperspectral Image Classification

    cs.CV 2026-08 conditional novelty 5.0 of 10

    A prototype-guided framework that separates positive from negative classification evidence and calibrates uncertain pixels reports state-of-the-art accuracy on three hyperspectral benchmarks, with internally inconsist...

  3. BCG-Former: Toward Pareto-Efficient Hyperspectral Image Classification via Band-Contextual Gating

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A 0.10–0.23M-parameter CNN-transformer with band-contextual gating, a spectral summary token, and single-pass Band-RoPE linear attention reports sub-millisecond inference and near-SOTA accuracy on eight HSI benchmarks.

  4. DCT-Mamba3D: Spectral Decorrelation and Spatial-Spectral Feature Extraction for Hyperspectral Image Classification

    cs.CV 2025-02 conditional novelty 5.0 of 10

    DCT-Mamba3D, a hybrid of 3D DCT decorrelation and a bidirectional Mamba state-space model, reports the highest classification accuracy on Indian Pines, KSC, and Houston2013 hyperspectral benchmarks.

  5. MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification

    cs.CV 2025-01 conditional novelty 5.0 of 10

    A pixel-level Mamba model with spatial and spectral branches reports state-of-the-art hyperspectral image classification on four datasets.

  6. MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone Architecture

    cs.CV 2025-07 reject novelty 4.0 of 10

    MVNet combines 3D-CNN, Transformer, and Mamba in a dual-branch design and claims 99%+ accuracy on three hyperspectral benchmarks, but the experimental reporting is internally inconsistent and the method is not reproducible.

  7. Hybrid State-Space and GRU-based Graph Tokenization Mamba for Hyperspectral Image Classification

    cs.CV 2025-02 reject novelty 3.0 of 10

    A GRU-based pipeline with convolutional tokens and graph attention is proposed for hyperspectral image classification, but the reported state-of-the-art claims are inconsistent with the paper's own experiments.

Pith tools