mlsanityData to 7 Oct 2026

Vision Mamba: A Comprehensive Survey and Taxonomy

arXiv 2405.04404 ↗First posted 7 May 2024cs.CV cs.AI cs.CLcited by 53

On the map: State-space sequence models (S4, Mamba) → Vision Mamba backbones

Abstract (arXiv)

State Space Model (SSM) is a mathematical model used to describe and analyze the behavior of dynamic systems. This model has witnessed numerous applications in several fields, including control theory, signal processing, economics and machine learning. In the field of deep learning, state space models are used to process sequence data, such as time series analysis, natural language processing (NLP) and video understanding. By mapping sequence data to state space, long-term dependencies in the data can be better captured. In particular, modern SSMs have shown strong representational capabilities in NLP, especially in long sequence modeling, while maintaining linear time complexity. Notably, based on the latest state-space models, Mamba merges time-varying parameters into SSMs and formulates a hardware-aware algorithm for efficient training and inference. Given its impressive efficiency and strong long-range dependency modeling capability, Mamba is expected to become a new AI architecture that may outperform Transformer. Recently, a number of works have attempted to study the potential of Mamba in various fields, such as general vision, multi-modal, medical image analysis and remote sensing image analysis, by extending Mamba from natural language domain to visual domain. To fully understand Mamba in the visual domain, we conduct a comprehensive survey and present a taxonomy study. This survey focuses on Mamba's application to a variety of visual tasks and data types, and discusses its predecessors, recent advances and far-reaching impact on a wide range of domains. Since Mamba is now on an upward trend, please actively notice us if you have new findings, and new progress on Mamba will be included in this survey in a timely manner and updated on the Mamba project at https://github.com/lx6c78/Vision-Mamba-A-Comprehensive-Survey-and-Taxonomy.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 126 of its 133 references that are in the map. First posted on arXiv 7 May 2024.

Builds on

126 of 133 references.

Closest ancestors · 16

Same direction, newest first

  1. 2024Visual Mamba: A Survey and New Outlooks29 Apr
  2. 2024A Survey on Visual Mamba24 Apr
  3. 2024A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion14 Apr
  4. 2024DGMamba: Domain Generalization via Generalized State Space Model11 Apr
  5. 2024Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation5 Apr
  6. 2024ReMamber: Referring Image Segmentation with Mamba Twister26 Mar
  7. 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition26 Mar
  8. 2024SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series22 Mar
  9. 2024Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference21 Mar
  10. 2024VL-Mamba: Exploring State Space Models for Multimodal Learning20 Mar
  11. 2024On the low-shot transferability of [V]-Mamba15 Mar
  12. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba15 Mar
4 more
  1. 2024LocalMamba: Visual State Space Model with Windowed Selective Scan14 Mar
  2. 2024Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning24 Feb
  3. 2024Pan-Mamba: Effective pan-sharpening with State Space Model19 Feb
  4. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model17 Jan

Other references · 110

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  8. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  10. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  11. 2017Squeeze-and-Excitation Networkscited by 4,763
  12. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
38 more
  1. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  2. 2022A ConvNet for the 2020scited by 3,545
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  4. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  5. 2021ViViT: A Video Vision Transformercited by 1,610
  6. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  7. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  8. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  9. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  10. 2024VMamba: Visual State Space Modelcited by 955
  11. 2020Designing Network Design Spacescited by 954
  12. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 823
  13. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  14. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
  15. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  16. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 600
  17. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  18. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 412
  19. 2023Resurrecting Recurrent Neural Networks for Long Sequencescited by 397
  20. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 350
  21. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  22. 2022AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentationcited by 347
  23. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  24. 20183D MRI brain tumor segmentation using autoencoder regularizationcited by 324
  25. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 286
  26. 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 266
  27. 2021TransFuse: Fusing Transformers and CNNs for Medical Image Segmentationcited by 258
  28. 2023Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancementcited by 228
  29. 2021nnFormer: Interleaved Transformer for Volumetric Segmentationcited by 179
  30. 2024Swin-UMamba: Mamba-based UNet with ImageNet-based pretrainingcited by 179
  31. 20192017 Robotic Instrument Segmentation Challengecited by 166
  32. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  33. 2024Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentationcited by 133
  34. 2024ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Modelcited by 118
  35. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  36. 2024Motion Mamba: Efficient and Long Sequence Motion Generationcited by 111
  37. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 106
  38. 2024RSMamba: Remote Sensing Image Classification with State Space Modelcited by 95

50 most cited of 110 All 110 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 12; 2025: 27; 2026: 14.

53 papers.

Sort:

By area:

  1. 2024I2I-Mamba: Multi-modal medical image synthesis via selective state space modelingcited by 26
  2. 2024MVGamba: Unify 3D Content Generation as State Space Sequence Modelingcited by 23
  3. 2024Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classificationcited by 18
  4. 2024Mamba in Vision: A Comprehensive Survey of Techniques and Applicationscited by 18
  5. 2024A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyondcited by 16
  6. 2024Multi-head Spatial-Spectral Mamba for Hyperspectral Image Classificationcited by 10
  7. 2024Physics-Driven Autoregressive State Space Models for Medical Image Reconstructioncited by 7
  8. 2025FlowState: Sampling-Rate-Equivariant Time-Series Forecastingcited by 7
  9. 2026ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understandingcited by 7
  10. 2024Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancementcited by 6
  11. 2024MatMamba: A Matryoshka State Space Modelcited by 6
  12. 2025Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlookcited by 6
38 more
  1. 2025SRMamba: Mamba for Super-Resolution of LiDAR Point Cloudscited by 5
  2. 2025RadioMamba: Breaking the Accuracy-Efficiency Trade-off in Radio Map Construction via a Hybrid Mamba-UNetcited by 5
  3. 2025VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representationcited by 4
  4. 2025DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbonecited by 4
  5. 2025DH-Mamba: Exploring Dual-domain Hierarchical State Space Models for MRI Reconstructioncited by 3
  6. 2025ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mambacited by 3
  7. 2026Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Modelscited by 3
  8. 2024Neural Architecture Search based Global-local Vision Mamba for Palm-Vein Recognitioncited by 2
  9. 2024Exploring Graph Mamba: A Comprehensive Survey on State-Space Models for Graph Learningcited by 2
  10. 2025Hybrid Vision Transformer-Mamba Framework for Autism Diagnosis via Eye-Tracking Analysiscited by 2
  11. 2025Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domainscited by 2
  12. 2025Kolmogorov-Arnold Network for Remote Sensing Image Semantic Segmentationcited by 1
  13. 2025Mamba-Based Ensemble learning for White Blood Cell Classificationcited by 1
  14. 2025Efficient LiDAR Reflectance Compression via Scanning Serializationcited by 1
  15. 2025MambaOutRS: A Hybrid CNN-Fourier Architecture for Remote Sensing Image Classificationcited by 1
  16. 2025Beyond Global Scanning: Adaptive Visual State Space Modeling for Salient Object Detection in Optical Remote Sensing Imagescited by 1
  17. 2025CMFDNet: Cross-Mamba and Feature Discovery Network for Polyp Segmentationcited by 1
  18. 2025CD-Mamba: Cloud detection with long-range spatial dependency modelingcited by 1
  19. 2025SlideMamba: Entropy-Based Adaptive Fusion of GNN and Mamba for Enhanced Representation Learning in Digital Pathologycited by 1
  20. 2025MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequencecited by 1
  21. 2025Memory as Resonance: A Biomimetic Architecture for Infinite Context Memory on Ergodic Phonetic Manifoldscited by 1
  22. 2026Partial Ring Scan: Revisiting Scan Order in Vision State Space Modelscited by 1
  23. 2026Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routingcited by 1
  24. 2024When Mamba Meets xLSTM: An Efficient and Precise Method with the xLSTM-VMUNet Model for Skin lesion Segmentationcited by 0
  25. 2025ECP-Mamba: An Efficient Multi-scale Self-supervised Contrastive Learning Method with State Space Model for PolSAR Image Classificationcited by 0
  26. 2025SSFMamba: Learning Symmetry-driven Spatial-Frequency Modeling for Physically Consistent 3D Medical Image Segmentationcited by 0
  27. 2025Sequential Token Merging: Revisiting Hidden Statescited by 0
  28. 2025HSNet: Heterogeneous Subgraph Network for Single Image Super-resolutioncited by 0
  29. 2025DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Derainingcited by 0
  30. 2025Trajectory-guided discharge stratification for heart failure using short-context electronic health record sequence modelingcited by 0
  31. 2025MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processingcited by 0
  32. 2026StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimationcited by 0
  33. 2026ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioningcited by 0
  34. 2026Unmixing-Guided Spatial-Spectral Mamba with Clustering Tokens for Hyperspectral Image Classificationcited by 0
  35. 2026ViM-Q: Scalable Algorithm-Hardware Co-Design for Vision Mamba Model Inference on FPGAcited by 0
  36. 2026Uncertainty-Guided Dual-Domain Learning for Reliable Skin Lesion Segmentationcited by 0
  37. 2026Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attentioncited by 0
  38. 2026DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Modelscited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025X-VMamba: Explainable Vision Mamba
  2. 2024State Space Models as Foundation Models: A Control Theoretic Overview
  3. 2024A Survey of Mamba
  4. 2025First-order State Space Model for Lightweight Image Super-resolution
  5. 2024Exploring the Capability of Mamba in Speech Applications
  6. 2024StableMamba: Distillation-free Scaling of Large SSMs for Images and Videos
  7. 2024Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain
  8. 2024MambaOut: Do We Really Need Mamba for Vision?