mlsanityData to 14 Oct 2026

Visual Mamba: A Survey and New Outlooks

arXiv 2404.18861 ↗First posted 29 Apr 2024cs.CVcited by 41

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

Abstract (arXiv)

Mamba, a recent selective structured state space model, excels in long sequence modeling, which is vital in the large model era. Long sequence modeling poses significant challenges, including capturing long-range dependencies within the data and handling the computational demands caused by their extensive length. Mamba addresses these challenges by overcoming the local perception limitations of convolutional neural networks and the quadratic computational complexity of Transformers. Given its advantages over these mainstream foundation architectures, Mamba exhibits great potential to be a visual foundation architecture. Since January 2024, Mamba has been actively applied to diverse computer vision tasks, yielding numerous contributions. To help keep pace with the rapid advancements, this paper reviews visual Mamba approaches, analyzing over 200 papers. This paper begins by delineating the formulation of the original Mamba model. Subsequently, it delves into representative backbone networks, and applications categorized using different modalities, including image, video, point cloud, and multi-modal data. Particularly, we identify scanning techniques as critical for adapting Mamba to vision tasks, and decouple these scanning techniques to clarify their functionality and enhance their flexibility across various applications. Finally, we discuss the challenges and future directions, providing insights into new outlooks in this fast evolving area. A comprehensive list of visual Mamba models reviewed in this work is available at https://github.com/Ruixxxx/Awesome-Vision-Mamba-Models.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 85 of its 168 references that are in the map. First posted on arXiv 29 Apr 2024.

Builds on

85 of 168 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion14 Apr
  2. 2024Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation5 Apr
  3. 2024ReMamber: Referring Image Segmentation with Mamba Twister26 Mar
  4. 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition26 Mar
  5. 2024Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference21 Mar
  6. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba15 Mar

Other references · 79

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  8. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  9. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  10. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  11. 2017Mask R-CNNcited by 7,277
  12. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
38 more
  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  3. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  4. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  5. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  6. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  7. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  8. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  9. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  10. 2020Designing Network Design Spacescited by 960
  11. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  12. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  13. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  14. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
  15. 2022Vision Transformer Adapter for Dense Predictionscited by 565
  16. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  17. 2022DeiT III: Revenge of the ViTcited by 419
  18. 2023Resurrecting Recurrent Neural Networks for Long Sequencescited by 408
  19. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 350
  20. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 328
  21. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  22. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 287
  23. 2021Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encodingcited by 207
  24. 2021VOLO: Vision Outlooker for Visual Recognitioncited by 165
  25. 2022How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projectionscited by 122
  26. 2024Motion Mamba: Efficient and Long Sequence Motion Generationcited by 112
  27. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 108
  28. 2024Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Taskscited by 105
  29. 2024The Hidden Attention of Mamba Modelscited by 91
  30. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  31. 2024MedMamba: Vision Mamba for Medical Image Classificationcited by 88
  32. 2024RS-Mamba for Large Remote Sensing Image Dense Predictioncited by 81
  33. 2024FusionMamba: Dynamic Feature Enhancement for Multimodal Image Fusion with Mambacited by 81
  34. 2022Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learningcited by 78
  35. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 73
  36. 2024Fusion-Mamba for Cross-modality Object Detectioncited by 67
  37. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  38. 2024FreqMamba: Viewing Mamba from a Frequency Perspective for Image Derainingcited by 57

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 20; 2025: 16; 2026: 5.

41 papers.

Sort:

By area:

  1. 2024Vision Mamba: A Comprehensive Survey and Taxonomycited by 54
  2. 2025MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classificationcited by 44
  3. 2024A Survey of Mambacited by 39
  4. 2024Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKVcited by 36
  5. 2024I2I-Mamba: Multi-modal medical image synthesis via selective state space modelingcited by 26
  6. 2024PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysiscited by 26
  7. 2024Matten: Video Generation with Mamba-Attentioncited by 24
  8. 2024MVGamba: Unify 3D Content Generation as State Space Sequence Modelingcited by 23
  9. 2024Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Surveycited by 23
  10. 2025SMamba: Sparse Mamba for Event-based Object Detectioncited by 19
  11. 2024Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classificationcited by 18
  12. 2024Mamba in Vision: A Comprehensive Survey of Techniques and Applicationscited by 18
29 more
  1. 2024A Comprehensive Survey of Mamba Architectures for Medical Image Analysis: Classification, Segmentation, Restoration and Beyondcited by 16
  2. 2024HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image Classificationcited by 13
  3. 2024Scalable Visual State Space Model with Fractal Scanningcited by 11
  4. 2025Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mambacited by 9
  5. 2024Exploring the Limitations of Mamba in COPY and CoT Reasoningcited by 6
  6. 2025Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlookcited by 6
  7. 2025DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbonecited by 6
  8. 2024HDMba: Hyperspectral Remote Sensing Imagery Dehazing with State Space Modelcited by 5
  9. 2024CT-Mamba: A Hybrid Convolutional State Space Model for Low-Dose CT Denoisingcited by 4
  10. 2025DH-Mamba: Exploring Dual-domain Hierarchical State Space Models for MRI Reconstructioncited by 3
  11. 2024EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignmentcited by 2
  12. 2024Vision Mamba: Cutting-Edge Classification of Alzheimer's Disease with 3D MRI Scanscited by 1
  13. 2025Kolmogorov-Arnold Network for Remote Sensing Image Semantic Segmentationcited by 1
  14. 2025Mamba-Based Ensemble learning for White Blood Cell Classificationcited by 1
  15. 2025Beyond Global Scanning: Adaptive Visual State Space Modeling for Salient Object Detection in Optical Remote Sensing Imagescited by 1
  16. 2025DIME-Net: A Dual-Illumination Adaptive Enhancement Network Based on Retinex and Mixture-of-Expertscited by 1
  17. 2025MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognitioncited by 1
  18. 2025MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Imagecited by 1
  19. 2025Efficient Vision Mamba for MRI Super-Resolution via Hybrid Selective Scanningcited by 1
  20. 2026PPC-MT: Parallel Point Cloud Completion with Mamba-Transformer Hybrid Architecturecited by 1
  21. 2024UMambaAdj: Advancing GTV Segmentation for Head and Neck Cancer in MRI-Guided RT with UMamba and nnU-Net ResEnc Plannercited by 0
  22. 2024Selective State Space Memory for Large Vision-Language Modelscited by 0
  23. 2025ECP-Mamba: An Efficient Multi-scale Self-supervised Contrastive Learning Method with State Space Model for PolSAR Image Classificationcited by 0
  24. 2025Few-Shot Object Detection via Spatial-Channel State Space Modelcited by 0
  25. 2025Beyond BEV: Optimizing Point-Level Tokens for Collaborative Perceptioncited by 0
  26. 2026How to Build Robust, Scalable Models for GSV-Based Indicators in Neighborhood Researchcited by 0
  27. 2026Scaling State-Space Models on Multiple GPUs with Tensor Parallelismcited by 0
  28. 2026ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioningcited by 0
  29. 2026Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Supportcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Survey on Visual Mamba
  2. 2024LocalMamba: Visual State Space Model with Windowed Selective Scan
  3. 2024MambaOut: Do We Really Need Mamba for Vision?
  4. 2025A Survey on Mamba Architecture for Vision Applications
  5. 2024Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
  6. 2026SF-Mamba: Rethinking State Space Model for Vision
  7. 2026MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models
  8. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Model